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

    Neuronpedia

    INDEX
    Explanations

    Code/Scientific notation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    utan
    -0.07
    티
    -0.07
    agination
    -0.07
    етич
    -0.06
     Radiation
    -0.06
     Flame
    -0.06
    orate
    -0.06
     Ελλά
    -0.06
     aided
    -0.06
    (define
    -0.06
    POSITIVE LOGITS
    .Σ
    0.07
    	main
    0.06
    419
    0.06
    ırken
    0.06
    ｣
    0.06
    INSTALL
    0.06
     Eylül
    0.06
    (Target
    0.06
    211
    0.06
    ){}↵
    0.06
    Act Density 0.010%

    No Known Activations