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

    Neuronpedia

    INDEX
    Explanations

    Dollar amounts/per

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    定的
    -0.08
    -proof
    -0.07
     considered
    -0.07
     Voldemort
    -0.07
    _API
    -0.07
    rawing
    -0.06
    我们的
    -0.06
     authoritarian
    -0.06
    گ
    -0.06
     между
    -0.06
    POSITIVE LOGITS
     McK
    0.07
    (^
    0.06
    cone
    0.06
    .organ
    0.06
    sys
    0.06
    978
    0.06
     soccer
    0.06
    sym
    0.06
     christian
    0.06
    onym
    0.06
    Act Density 0.012%

    No Known Activations