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

    Neuronpedia

    INDEX
    Explanations

    G

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    據
    -0.08
     !"
    -0.07
    _access
    -0.07
    条件
    -0.06
    ты
    -0.06
    兒
    -0.06
    isseur
    -0.06
    isation
    -0.06
     inoc
    -0.06
     sonuç
    -0.06
    POSITIVE LOGITS
     Deploy
    0.08
     NYPD
    0.08
    .ComponentPlacement
    0.07
    яз
    0.07
    キャンペ
    0.07
     getopt
    0.07
    〽
    0.07
    .Evaluate
    0.07
     akş
    0.07
     люб
    0.07
    Act Density 0.477%

    No Known Activations