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

    Neuronpedia

    INDEX
    Explanations

    better

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    month
    -0.06
    plet
    -0.06
    、お
    -0.06
    )new
    -0.06
    /output
    -0.06
    くれ
    -0.06
    sol
    -0.06
    .Roll
    -0.06
    üçük
    -0.06
    ,options
    -0.06
    POSITIVE LOGITS
    Except
    0.07
     ipAddress
    0.07
     dk
    0.07
     abrasive
    0.07
    _ready
    0.06
     Classification
    0.06
    Recv
    0.06
     Lesbian
    0.06
     winds
    0.06
    WA
    0.06
    Act Density 0.000%

    No Known Activations