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

    Neuronpedia

    INDEX
    Explanations

    binary or squared

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     мало
    -0.07
    (bc
    -0.07
    (cur
    -0.07
    .trace
    -0.07
     ном
    -0.07
    agini
    -0.07
    าส
    -0.06
    urvey
    -0.06
    ห
    -0.06
    (mp
    -0.06
    POSITIVE LOGITS
     Potion
    0.06
     daily
    0.06
    _filepath
    0.06
     Wheel
    0.06
    067
    0.06
     backlight
    0.06
    ).'
    0.06
    _BACK
    0.06
    ',
↵
    0.06
     Assistant
    0.06
    Act Density 0.010%

    No Known Activations