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

    Neuronpedia

    INDEX
    Explanations

    increase

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     فرض
    -0.07
     нем
    -0.06
     grinned
    -0.06
     jedním
    -0.06
     beg
    -0.06
     сделать
    -0.06
     �
    -0.06
     Поч
    -0.06
    йте
    -0.06
     Pf
    -0.06
    POSITIVE LOGITS
    同步
    0.07
     calidad
    0.06
    .Throw
    0.06
    _weather
    0.06
     ranger
    0.06
     cose
    0.06
    ';↵↵↵
    0.06
    .motion
    0.06
     stellt
    0.06
     må
    0.06
    Act Density 0.025%

    No Known Activations