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

    Neuronpedia

    INDEX
    Explanations

    cause

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     blends
    -0.07
    todos
    -0.07
    _alarm
    -0.06
    Sans
    -0.06
    osph
    -0.06
    073
    -0.06
     Astro
    -0.06
     erm
    -0.06
    كون
    -0.06
     submissions
    -0.06
    POSITIVE LOGITS
     связи
    0.07
     základ
    0.06
    lya
    0.06
     ~(
    0.06
     velké
    0.06
     قتل
    0.06
    处
    0.06
     Freeman
    0.06
    ":"/
    0.06
     zah
    0.06
    Act Density 0.002%

    No Known Activations