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

    Neuronpedia

    INDEX
    Explanations

    Code and general language

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     murderous
    -0.07
    ﾟ
    -0.07
     threatens
    -0.06
     "*",
    -0.06
    利
    -0.06
     tấn
    -0.06
    戸
    -0.06
    ','=','
    -0.06
     Nr
    -0.06
    нить
    -0.06
    POSITIVE LOGITS
     WOW
    0.07
     feather
    0.07
    iferay
    0.06
    ंगल
    0.06
    Ended
    0.06
     �
    0.06
    ovies
    0.06
     teplot
    0.06
    Windows
    0.06
    ƒ
    0.06
    Act Density 0.000%

    No Known Activations