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

    Neuronpedia

    INDEX
    Explanations

    Code/Interface Text

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     expans
    -0.07
    `)↵
    -0.06
     Init
    -0.06
    .What
    -0.06
    ,$
    -0.06
     legality
    -0.06
     přísluš
    -0.06
    Effective
    -0.06
     executive
    -0.06
    Constraint
    -0.06
    POSITIVE LOGITS
     dov
    0.07
    amy
    0.07
    	sign
    0.07
    ısına
    0.07
    (extra
    0.06
    mile
    0.06
    uteč
    0.06
     ฿
    0.06
    rians
    0.06
    caff
    0.06
    Act Density 0.003%

    No Known Activations