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

    Neuronpedia

    INDEX
    Explanations

    screen orientation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     kazanç
    -0.07
    روب
    -0.07
     Playback
    -0.07
    -x
    -0.07
    lbl
    -0.06
     lässt
    -0.06
     μπορεί
    -0.06
     textField
    -0.06
    ضوع
    -0.06
    iske
    -0.06
    POSITIVE LOGITS
    +");↵
    0.07
     mul
    0.07
     snatch
    0.07
     Vall
    0.06
     scout
    0.06
    ザイン
    0.06
    .Command
    0.06
     Dul
    0.06
     basically
    0.06
    grab
    0.06
    Act Density 0.007%

    No Known Activations