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

    Neuronpedia

    INDEX
    Explanations

    answers or lists

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     примерно
    -0.08
     infatti
    -0.08
     Eleg
    -0.07
     coef
    -0.07
     ungef
    -0.07
     Often
    -0.07
     בהתאם
    -0.07
    	with
    -0.07
     oldukça
    -0.07
    including
    -0.07
    POSITIVE LOGITS
     magically
    0.11
     necesariamente
    0.10
     zomaar
    0.10
     quelcon
    0.09
     solely
    0.09
     inherently
    0.09
     necessariamente
    0.09
     diretamente
    0.08
    直接
    0.08
     collaps
    0.08
    Act Density 0.087%

    No Known Activations