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

    Neuronpedia

    INDEX
    Explanations

    Code or file paths

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     sigue
    -0.08
    ynı
    -0.07
     AppComponent
    -0.07
    žení
    -0.07
     która
    -0.07
     располож
    -0.07
     carts
    -0.07
     جميع
    -0.07
     velké
    -0.07
    เส
    -0.06
    POSITIVE LOGITS
     MSR
    0.06
     mural
    0.06
     silicone
    0.06
     salesman
    0.06
     아이
    0.06
    atoon
    0.06
     Deployment
    0.06
     modal
    0.06
    rpc
    0.06
    _within
    0.06
    Act Density 0.000%

    No Known Activations