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

    Neuronpedia

    INDEX
    Explanations

    on

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    chalk
    -0.07
    ugar
    -0.06
    òn
    -0.06
     tornado
    -0.06
    lerdi
    -0.06
    -income
    -0.06
    lite
    -0.06
     티
    -0.06
     roc
    -0.06
     viên
    -0.06
    POSITIVE LOGITS
    Aside
    0.07
    럽
    0.06
     помощ
    0.06
     nelle
    0.06
    .rec
    0.06
     translate
    0.06
     summon
    0.06
    	Token
    0.06
     HACK
    0.06
    	reader
    0.06
    Act Density 0.017%

    No Known Activations