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

    Neuronpedia

    INDEX
    Explanations

    feed

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _|
    -0.06
    definition
    -0.06
    amento
    -0.06
     Watching
    -0.06
    /Create
    -0.06
    [y
    -0.06
    	Write
    -0.06
    ytic
    -0.05
     Spam
    -0.05
    %;">
    -0.05
    POSITIVE LOGITS
    urm
    0.09
    さい
    0.07
     almak
    0.07
    ۲۱
    0.07
    429
    0.07
     alcoholic
    0.07
    -indent
    0.07
    687
    0.06
    .Ext
    0.06
    reverse
    0.06
    Act Density 0.014%

    No Known Activations