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

    Neuronpedia

    INDEX
    Explanations

    hosting events

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     west
    -0.08
    เอ
    -0.08
     Gur
    -0.08
     antibiot
    -0.08
    agli
    -0.08
     spared
    -0.07
     ago
    -0.07
     ವಿರುದ್ಧ
    -0.07
     Gra
    -0.07
     sanctuary
    -0.07
    POSITIVE LOGITS
    主持
    0.12
     अभिनेत्री
    0.09
    nv
    0.08
    कर्त
    0.08
    .Main
    0.08
     उद्घ
    0.08
     personalities
    0.08
    ning
    0.08
    कर्ताओं
    0.08
    ندگان
    0.08
    Act Density 0.022%

    No Known Activations