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

    Neuronpedia

    INDEX
    Explanations

    Code/data

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     precisely
    -0.08
     Conveyor
    -0.07
    .con
    -0.07
    컨
    -0.07
    .Conn
    -0.07
     somewhere
    -0.07
    ceans
    -0.07
    窄
    -0.07
    .constants
    -0.07
    无所
    -0.06
    POSITIVE LOGITS
    我看
    0.07
    acha
    0.07
    _RESOLUTION
    0.07
    isFunction
    0.06
    _FAILED
    0.06
    .words
    0.06
    invite
    0.06
     איש
    0.06
    .notifications
    0.06
     الأيام
    0.06
    Act Density 0.049%

    No Known Activations