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

    Neuronpedia

    INDEX
    Explanations

    the

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     ashamed
    -0.07
     proof
    -0.07
     retorna
    -0.06
    ('~
    -0.06
    ')['
    -0.06
    .pageX
    -0.06
     Protector
    -0.06
     req
    -0.06
    @Transactional
    -0.06
    :key
    -0.06
    POSITIVE LOGITS
    179
    0.07
     тысяч
    0.06
    Arizona
    0.06
     abi
    0.06
    added
    0.06
    mse
    0.06
     territor
    0.06
     Jerry
    0.06
     RESP
    0.06
     tweets
    0.06
    Act Density 0.002%

    No Known Activations