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

    Neuronpedia

    INDEX
    Explanations

    Scores in a competition

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    tu
    -0.07
    Unfortunately
    -0.06
    lasses
    -0.06
    emes
    -0.06
    plaint
    -0.06
    argins
    -0.06
    ecast
    -0.06
    UE
    -0.06
    ecut
    -0.06
    enu
    -0.06
    POSITIVE LOGITS
    (Arrays
    0.07
    CallCheck
    0.06
    _number
    0.06
    รอบ
    0.06
    _extend
    0.06
     punct
    0.06
     litt
    0.06
    _tabs
    0.06
     RTP
    0.06
     INV
    0.06
    Act Density 0.017%

    No Known Activations