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

    Neuronpedia

    INDEX
    Explanations

    terms related to model identification and its properties

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

    assumptions and identifiability

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     PagesJaunes
    -0.49
    bootstrapcdn
    -0.47
     Numerade
    -0.46
    RemoveField
    -0.43
     مشين
    -0.43
     ब्रेकडाउन
    -0.42
     Theſe
    -0.41
     wikipagina
    -0.40
     صوتيه
    -0.39
    antic
    -0.36
    POSITIVE LOGITS
     الاطلاع
    0.46
     Calibration
    0.43
     fit
    0.43
     calibrate
    0.41
     onlyOwner
    0.41
    InjectAttribute
    0.40
     calibr
    0.39
     calibration
    0.39
    enquête
    0.39
     Trustee
    0.39
    Act Density 0.503%

    No Known Activations