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

    Neuronpedia

    INDEX
    Explanations

    crimes

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    keydown
    -0.07
    zelf
    -0.06
     gör
    -0.06
     причин
    -0.06
    کم
    -0.06
    ixel
    -0.06
    aln
    -0.06
    odes
    -0.06
    Kn
    -0.06
     Penis
    -0.06
    POSITIVE LOGITS
     अगर
    0.07
    πος
    0.07
     hoch
    0.07
     userService
    0.06
    ุก
    0.06
    .setToolTipText
    0.06
     grands
    0.06
     veel
    0.06
     assertTrue
    0.06
    fresh
    0.06
    Act Density 0.012%

    No Known Activations