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

    Neuronpedia

    INDEX
    Explanations

    quotation mark

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ografia
    -0.07
     Board
    -0.07
    крут
    -0.07
    超强
    -0.07
     trance
    -0.07
    :ss
    -0.06
     eer
    -0.06
    <TSource
    -0.06
     revoke
    -0.06
     Marty
    -0.06
    POSITIVE LOGITS
    _rand
    0.07
     an
    0.07
    .LinearLayoutManager
    0.07
     constructs
    0.07
     TOKEN
    0.07
    atively
    0.07
    这般
    0.07
    an
    0.07
     "#"
    0.07
     ALPHA
    0.06
    Act Density 0.001%

    No Known Activations