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

    Neuronpedia

    INDEX
    Explanations

    до

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     pounding
    -0.07
     Cyrus
    -0.06
    .UltraWin
    -0.06
    Prototype
    -0.06
     pipes
    -0.06
     مایل
    -0.06
    .google
    -0.06
     textile
    -0.06
     sb
    -0.06
     Valid
    -0.06
    POSITIVE LOGITS
    istration
    0.07
    calc
    0.07
    polator
    0.06
     منه
    0.06
    -contact
    0.06
     الحر
    0.06
    .DialogResult
    0.06
    _TO
    0.06
     dizzy
    0.06
    ả
    0.06
    Act Density 0.007%

    No Known Activations