Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    quantifiable or numerical values and comparisons related to counts or positions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Quantities or measurements

    np_acts-logits-general · gemini-2.0-flash

    quantities and steps

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    цездатний
    -0.57
    IntoConstraints
    -0.56
     resourceCulture
    -0.56
    djangoproject
    -0.55
    layoutControl
    -0.55
    TextWatcher
    -0.53
     ElementRef
    -0.52
    gående
    -0.50
    Diweddarwch
    -0.49
    TagMode
    -0.48
    POSITIVE LOGITS
     step
    0.97
     steps
    0.91
     notches
    0.86
     rung
    0.83
     notch
    0.82
    step
    0.77
    steps
    0.76
     krok
    0.71
     كومونز
    0.65
    notch
    0.65
    Act Density 0.229%

    No Known Activations