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

    Neuronpedia

    INDEX
    Explanations

    researchers

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    اضی
    -0.06
     strengths
    -0.06
     Dialogue
    -0.06
    .vert
    -0.06
     Connections
    -0.06
     panicked
    -0.06
    On
    -0.06
     rue
    -0.06
    Difference
    -0.05
     night
    -0.05
    POSITIVE LOGITS
     زیرا
    0.07
     readdir
    0.06
     चल
    0.06
     rámci
    0.06
    .AL
    0.06
     sağlayan
    0.06
    Exp
    0.06
    entin
    0.06
    ствие
    0.06
    pets
    0.06
    Act Density 0.025%

    No Known Activations