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

    Neuronpedia

    INDEX
    Explanations

    magnitude

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     交
    -0.07
    份
    -0.07
     DRM
    -0.06
     ス
    -0.06
     스트
    -0.06
    laş
    -0.06
    тоф
    -0.06
     Screen
    -0.06
     invaluable
    -0.06
    sss
    -0.06
    POSITIVE LOGITS
     magnitude
    0.12
    magnitude
    0.09
    ians
    0.06
    High
    0.06
     babes
    0.06
    Magnitude
    0.06
     hungry
    0.06
    lords
    0.06
    чины
    0.06
    þ
    0.06
    Act Density 0.003%

    No Known Activations