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

    Neuronpedia

    INDEX
    Explanations

    leads

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     responseType
    -0.06
     constituents
    -0.06
    .toFixed
    -0.06
     oby
    -0.06
     Stall
    -0.06
    transpose
    -0.06
    十分
    -0.06
    944
    -0.06
    _mix
    -0.06
    _should
    -0.06
    POSITIVE LOGITS
    原来
    0.07
     QUAL
    0.06
     DE
    0.06
     effectively
    0.06
    itchen
    0.06
     гар
    0.06
    fat
    0.06
    :no
    0.06
    Standing
    0.06
    acula
    0.06
    Act Density 0.000%

    No Known Activations