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

    Neuronpedia

    INDEX
    Explanations

    answers

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     prescription
    -0.06
    碼
    -0.06
    一个人
    -0.06
    65
    -0.06
    (fontSize
    -0.06
    FF
    -0.06
    Bruce
    -0.05
     саме
    -0.05
    EDIUM
    -0.05
     indirect
    -0.05
    POSITIVE LOGITS
    _capture
    0.07
     frec
    0.07
    utta
    0.07
    ुब
    0.07
    کیل
    0.07
     bead
    0.07
     Spurs
    0.06
    WebResponse
    0.06
    .FormBorderStyle
    0.06
     صح
    0.06
    Act Density 0.008%

    No Known Activations