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

    Neuronpedia

    INDEX
    Explanations

    active/passive

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    itical
    -0.29
    arya
    -0.28
     characteristic
    -0.27
    iri
    -0.26
    iaux
    -0.25
    åĬŁ
    -0.25
    op
    -0.25
    enschaft
    -0.24
     genetic
    -0.24
    opp
    -0.24
    POSITIVE LOGITS
    mailto
    0.27
    åĪ°ä½į
    0.26
    oose
    0.26
    éĦĹ
    0.25
    crets
    0.25
    proved
    0.25
    dyn
    0.25
     saliva
    0.25
     whisper
    0.24
    ainted
    0.24
    Act Density 0.348%

    No Known Activations