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

    Neuronpedia

    INDEX
    Explanations

    technical descriptions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     NOT
    -0.07
     grads
    -0.07
    better
    -0.06
    bit
    -0.06
    EVER
    -0.06
    ML
    -0.06
    Plate
    -0.06
    bies
    -0.06
     compareTo
    -0.06
     automated
    -0.06
    POSITIVE LOGITS
    �
    0.06
     disse
    0.06
     नगर
    0.06
    арь
    0.06
    ("${
    0.06
     교
    0.06
     spender
    0.06
    _qs
    0.06
     автомоб
    0.06
    �
    0.06
    Act Density 0.424%

    No Known Activations