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

    Neuronpedia

    INDEX
    Explanations

    Education/Training

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     socialism
    -0.07
     найти
    -0.07
    协会
    -0.07
    🚬
    -0.07
    VPN
    -0.06
    亲人
    -0.06
     Parish
    -0.06
    riors
    -0.06
     Làm
    -0.06
    ENCES
    -0.06
    POSITIVE LOGITS
    墨
    0.08
     Affordable
    0.07
    蟛
    0.07
     sought
    0.07
     hObject
    0.07
    مج
    0.06
    _specific
    0.06
     whirl
    0.06
     ogr
    0.06
    vanized
    0.06
    Act Density 0.151%

    No Known Activations