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

    Neuronpedia

    INDEX
    Explanations

    Parenthesis

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Look
    -0.07
    .median
    -0.07
     legalize
    -0.07
    /tutorial
    -0.07
    LOOK
    -0.07
     aids
    -0.06
     reson
    -0.06
     YEAR
    -0.06
     hop
    -0.06
     errorMsg
    -0.06
    POSITIVE LOGITS
     ControllerBase
    0.06
     vigil
    0.06
     Qin
    0.06
     samostat
    0.06
    leine
    0.06
    俺は
    0.06
    BOOLE
    0.06
    ões
    0.06
     آبی
    0.06
    бо
    0.06
    Act Density 0.132%

    No Known Activations