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

    Neuronpedia

    INDEX
    Explanations

    diseases

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _form
    -0.08
    (packet
    -0.07
     कप
    -0.07
     졸
    -0.07
    orary
    -0.07
     Charm
    -0.06
    _recall
    -0.06
     ":"
    -0.06
     Blocked
    -0.06
    (Document
    -0.06
    POSITIVE LOGITS
     Yosh
    0.06
     euth
    0.06
     Fallon
    0.06
    fails
    0.06
     Math
    0.06
     Localization
    0.05
    845
    0.05
    CartItem
    0.05
     mise
    0.05
    uncate
    0.05
    Act Density 0.007%

    No Known Activations