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

    Neuronpedia

    INDEX
    Explanations

    Negative reviews

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    caffold
    -0.07
    rowsers
    -0.07
    patient
    -0.07
     evenings
    -0.07
    .alloc
    -0.07
    湾
    -0.06
    clip
    -0.06
    learn
    -0.06
    words
    -0.06
    _emit
    -0.06
    POSITIVE LOGITS
    populate
    0.06
     Receive
    0.06
    Suggestions
    0.06
     öncelik
    0.06
     unthinkable
    0.06
     rfl
    0.06
     sesame
    0.06
     Sal
    0.06
     useClass
    0.06
     Naturally
    0.06
    Act Density 0.047%

    No Known Activations