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

    Neuronpedia

    INDEX
    Explanations

    Code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    /t
    -0.07
     Maintenance
    -0.06
     letech
    -0.06
     František
    -0.06
     heroine
    -0.06
     patch
    -0.06
    ATIC
    -0.06
    _VENDOR
    -0.06
     maintenance
    -0.06
     October
    -0.06
    POSITIVE LOGITS
    tığ
    0.07
     togg
    0.06
    лександ
    0.06
    ctica
    0.06
     joe
    0.06
    '&&
    0.06
     nhà
    0.06
    柳
    0.06
    _todo
    0.06
    tam
    0.06
    Act Density 0.018%

    No Known Activations