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

    Neuronpedia

    INDEX
    Explanations

    Legal language

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ファ
    -0.07
    Separ
    -0.07
    己
    -0.07
    <Client
    -0.07
    Deferred
    -0.06
     gender
    -0.06
     scaffold
    -0.06
    _spec
    -0.06
    atsapp
    -0.06
    	flex
    -0.06
    POSITIVE LOGITS
    dın
    0.06
    	on
    0.06
    -operative
    0.06
    .flag
    0.06
     Prozent
    0.06
    akeFromNib
    0.06
    قه
    0.06
     trolls
    0.06
     hoe
    0.06
    inen
    0.06
    Act Density 0.024%

    No Known Activations