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

    Neuronpedia

    INDEX
    Explanations

    code/math symbols

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    安排
    -0.07
     κον
    -0.07
    uffle
    -0.06
    PLIER
    -0.06
    OLUMNS
    -0.06
    returned
    -0.06
     sts
    -0.06
    dex
    -0.06
    uffles
    -0.06
    usters
    -0.06
    POSITIVE LOGITS
    !="
    0.07
     eff
    0.07
    Disposed
    0.07
    	inst
    0.06
    �
    0.06
    lerinin
    0.06
     realizado
    0.06
    (".
    0.06
     aktar
    0.06
    ump
    0.06
    Act Density 0.030%

    No Known Activations