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

    Neuronpedia

    INDEX
    Explanations

    domains ending in .com

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     macam
    1.50
     siquiera
    1.50
     visualizar
    1.42
    Jadi
    1.38
    hAP
    1.34
    !">
    1.34
     muffin
    1.32
     chùa
    1.30
    ه
    1.30
     heißt
    1.29
    POSITIVE LOGITS
    ian
    1.47
    .
    1.47
    ure
    1.38
    ic
    1.38
    ant
    1.33
    isphere
    1.31
    attie
    1.23
    ary
    1.20
    upp
    1.13
    itrile
    1.13
    Act Density 0.018%

    No Known Activations