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

    Neuronpedia

    INDEX
    Explanations

    head of

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    シュ
    -0.07
     Briggs
    -0.07
     peri
    -0.06
     LET
    -0.06
    .sf
    -0.06
     Injector
    -0.06
    _commands
    -0.06
    demo
    -0.06
     BW
    -0.06
    	priv
    -0.06
    POSITIVE LOGITS
    申请
    0.06
    ("\"
    0.06
    crew
    0.06
    Seattle
    0.06
     Fantasy
    0.06
     国家
    0.06
    時に
    0.05
     способ
    0.05
     gamm
    0.05
     zamanda
    0.05
    Act Density 0.024%

    No Known Activations