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

    Neuronpedia

    INDEX
    Explanations

    tor

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    biased
    -0.07
    secured
    -0.07
    .eof
    -0.06
     Gaming
    -0.06
    cams
    -0.06
    么
    -0.06
     explanations
    -0.06
    ERP
    -0.06
    (plane
    -0.06
     راهنم
    -0.06
    POSITIVE LOGITS
     turning
    0.07
     magically
    0.06
     thai
    0.06
     обычно
    0.06
    BIND
    0.06
    itar
    0.06
    他的
    0.06
     dividing
    0.06
     درجة
    0.06
     becomes
    0.06
    Act Density 0.017%

    No Known Activations