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

    Neuronpedia

    INDEX
    Explanations

    ":"

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ῆς
    -0.07
     være
    -0.07
    应该
    -0.06
     apprent
    -0.06
    ок
    -0.06
    itr
    -0.06
    	assertNotNull
    -0.06
    signin
    -0.06
    zl
    -0.06
    Cancelable
    -0.06
    POSITIVE LOGITS
     :
    0.08
    IGHT
    0.07
    xdf
    0.06
     kap
    0.06
    EXPORT
    0.06
    :function
    0.06
    戸
    0.06
     Yu
    0.06
     thương
    0.06
     din
    0.06
    Act Density 0.001%

    No Known Activations