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

    Neuronpedia

    INDEX
    Explanations

    movie related

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Shortcut
    -0.07
    /grid
    -0.06
     Institutional
    -0.06
     remedies
    -0.06
    ジョ
    -0.06
     onemocnění
    -0.06
     intest
    -0.06
    _need
    -0.06
    I
    -0.06
    IRROR
    -0.06
    POSITIVE LOGITS
     baud
    0.07
    _inf
    0.06
     onMouse
    0.06
    ่าม
    0.06
     rally
    0.06
     adapting
    0.06
    己
    0.06
    ft
    0.06
    五月
    0.06
     ще
    0.06
    Act Density 0.029%

    No Known Activations