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

    Neuronpedia

    INDEX
    Explanations

    through

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     upward
    -0.06
     ateş
    -0.06
     nasal
    -0.06
     adec
    -0.06
    ydı
    -0.06
    enso
    -0.06
     університет
    -0.06
    679
    -0.06
     hoy
    -0.06
     eoqkrvldkf
    -0.06
    POSITIVE LOGITS
     through
    0.08
    Formatter
    0.07
     undergo
    0.07
    ::::::
    0.07
     undergone
    0.07
     completeness
    0.07
    /Card
    0.07
     verbally
    0.07
    逐
    0.07
    hiro
    0.07
    Act Density 0.017%

    No Known Activations