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

    Neuronpedia

    INDEX
    Explanations

    heights

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ソン
    -0.07
     fasc
    -0.06
    ifference
    -0.06
    Năm
    -0.06
    뷰
    -0.06
     Stre
    -0.06
    岗
    -0.06
     zip
    -0.06
     semaine
    -0.06
    cccc
    -0.06
    POSITIVE LOGITS
     Mik
    0.07
    =";↵
    0.07
     unary
    0.06
    _weights
    0.06
    upyter
    0.06
    \Command
    0.06
    ulas
    0.06
     Corinth
    0.06
    ेग
    0.06
     Kon
    0.06
    Act Density 0.000%

    No Known Activations