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

    Neuronpedia

    INDEX
    Explanations

    :

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     dramas
    -0.08
    sWith
    -0.07
    را
    -0.07
     Trophy
    -0.07
     whiteColor
    -0.07
    \Collections
    -0.07
     fitte
    -0.07
    Раз
    -0.06
    Analyzer
    -0.06
    -Israel
    -0.06
    POSITIVE LOGITS
     κ
    0.06
    adox
    0.06
    elm
    0.06
    kj
    0.06
    (Me
    0.06
     hj
    0.06
    кет
    0.05
    _rate
    0.05
    _SZ
    0.05
    形式
    0.05
    Act Density 0.000%

    No Known Activations