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

    Neuronpedia

    INDEX
    Explanations

    free access

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     thinly
    -0.07
     experimentation
    -0.07
     Cognitive
    -0.07
    AccessorType
    -0.07
    Duplicate
    -0.07
    DataContract
    -0.07
    riad
    -0.07
     בחיי
    -0.07
    różni
    -0.07
    数字
    -0.07
    POSITIVE LOGITS
     unequiv
    0.07
    থ
    0.07
     PR
    0.07
     ma
    0.07
     sid
    0.07
    .throw
    0.07
    പ
    0.07
     INS
    0.07
    朋
    0.07
    Play
    0.07
    Act Density 0.040%

    No Known Activations