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

    Neuronpedia

    INDEX
    Explanations

    punctuation

    np_max-act-logits · gemini-2.0-flashTriggered by @majianfei030706
    New Auto-Interp
    Negative Logits
    IndexOf
    -0.06
    -version
    -0.06
     hurry
    -0.06
    ())
    -0.06
     ji
    -0.06
    subseteq
    -0.06
    ########################################################################
    -0.06
    Cut
    -0.06
     membership
    -0.06
    让
    -0.06
    POSITIVE LOGITS
     UIAlertView
    0.07
    armac
    0.06
    iards
    0.06
    izont
    0.06
     následující
    0.06
     entrada
    0.06
    ,:);↵
    0.06
    ulaire
    0.06
     зв
    0.06
    šení
    0.06
    Act Density 0.069%

    No Known Activations