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

    Neuronpedia

    INDEX
    Explanations

    A

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Stud
    -0.07
     ',↵
    -0.07
     brushes
    -0.06
    )))↵↵
    -0.06
     '>'
    -0.06
    uD
    -0.06
    _SF
    -0.06
    ',
    -0.06
    AMIL
    -0.06
    ».
    -0.06
    POSITIVE LOGITS
    医
    0.07
    Vintage
    0.07
     Vintage
    0.07
    sigmoid
    0.07
    inality
    0.06
     Founder
    0.06
     atrib
    0.06
    .onOptionsItemSelected
    0.06
     Ember
    0.06
     incumbent
    0.06
    Act Density 0.001%

    No Known Activations