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

    Neuronpedia

    INDEX
    Explanations

    references to various types of pigments and sediments

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

    pigment and -ment words

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    blå
    -0.54
    qü
    -0.51
    eyes
    -0.50
     nicio
    -0.50
    NoSuch
    -0.48
     pitié
    -0.48
     aéro
    -0.47
     Púb
    -0.47
    tagext
    -0.46
     auroit
    -0.46
    POSITIVE LOGITS
    ment
    0.80
    gement
    0.79
    ement
    0.78
    tement
    0.77
    vement
    0.75
    entation
    0.75
    lament
    0.73
    rament
    0.71
     ment
    0.71
    iment
    0.69
    Act Density 0.021%

    No Known Activations