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
    .indices
    -0.06
    -catching
    -0.06
     moss
    -0.06
     message
    -0.06
    Transform
    -0.06
     PSD
    -0.06
    .appendChild
    -0.06
    .questions
    -0.06
     нему
    -0.06
    .Visible
    -0.06
    POSITIVE LOGITS
    رخ
    0.07
    аторы
    0.06
     채
    0.06
    atore
    0.06
     gateway
    0.06
    رة
    0.06
    Envelope
    0.06
     entre
    0.06
    )\<
    0.06
     Reduced
    0.06
    Act Density 0.001%

    No Known Activations