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

    Neuronpedia

    INDEX
    Explanations

    alternative histories

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    nameof
    -0.07
     Lol
    -0.07
    Escape
    -0.07
    看
    -0.07
     constitu
    -0.07
    隈
    -0.07
     insisting
    -0.07
     impeachment
    -0.07
     repro
    -0.07
    Ele
    -0.07
    POSITIVE LOGITS
    Skills
    0.08
    argout
    0.08
    IntegerField
    0.07
    _written
    0.07
    	port
    0.07
    ㎎
    0.07
    /Set
    0.07
     אישי
    0.06
    Site
    0.06
    .errors
    0.06
    Act Density 0.025%

    No Known Activations