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

    Neuronpedia

    INDEX
    Explanations

    set

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     frustrating
    -0.06
     outputPath
    -0.06
    符
    -0.06
    ]').
    -0.06
     surrounding
    -0.06
    貸
    -0.06
    .power
    -0.06
    errmsg
    -0.06
     vorhand
    -0.06
    ))/
    -0.06
    POSITIVE LOGITS
    WN
    0.07
    _TYP
    0.07
    bee
    0.06
    γορ
    0.06
    leneck
    0.06
    LV
    0.06
     cert
    0.06
    	className
    0.06
     uint
    0.06
    Ин
    0.06
    Act Density 0.016%

    No Known Activations