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
     شدند
    -0.07
    .fft
    -0.07
    벌
    -0.07
     ashamed
    -0.06
    erten
    -0.06
     فر
    -0.06
     건
    -0.06
    shops
    -0.06
    -angular
    -0.06
    ostream
    -0.06
    POSITIVE LOGITS
     Logic
    0.07
    打
    0.06
    _float
    0.06
    0.06
    0.06
         
    0.06
     onay
    0.06
    한다
    0.06
     advance
    0.06
     Magic
    0.06
    Act Density 0.001%

    No Known Activations