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

    Neuronpedia

    INDEX
    Explanations

    UTF

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    sl
    -0.06
    /art
    -0.06
     пы
    -0.06
    志
    -0.06
     wilt
    -0.06
     consent
    -0.06
    ape
    -0.06
    animal
    -0.06
     Angiosper
    -0.06
    _RETURN
    -0.06
    POSITIVE LOGITS
    readcrumbs
    0.07
    UTF
    0.06
    ()↵↵↵
    0.06
    	ST
    0.06
    [System
    0.06
     LENGTH
    0.06
     Lisa
    0.06
    ↵  ↵
    0.06
     нарез
    0.06
     Ist
    0.06
    Act Density 0.001%

    No Known Activations