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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Debugger
    -0.07
     AppComponent
    -0.07
    帘
    -0.07
     activ
    -0.06
    restore
    -0.06
     programming
    -0.06
    压抑
    -0.06
    _png
    -0.06
    漠
    -0.06
     scr
    -0.06
    POSITIVE LOGITS
    	await
    0.07
     Romans
    0.07
    olves
    0.07
    clid
    0.07
    你会
    0.07
    ꪻ
    0.07
    븐
    0.06
    来历
    0.06
    ▢
    0.06
    läuft
    0.06
    Act Density 0.016%

    No Known Activations