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

    Neuronpedia

    INDEX
    Explanations

    solving problemssocial classificationcontent filteringaffords lodgingforce conversion

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Exo
    0.42
     Emerson
    0.41
     Inclusion
    0.41
     Leonardo
    0.41
     rampage
    0.40
     Pacquiao
    0.40
     Outreach
    0.40
     Comando
    0.40
     Watanabe
    0.40
     Schre
    0.39
    POSITIVE LOGITS
    semantic
    0.45
    composer
    0.43
    arsipkan
    0.43
    ູ
    0.43
    కం
    0.42
    rowset
    0.42
    креп
    0.41
    一張
    0.41
    ೋಗ
    0.41
    oxidation
    0.41
    Act Density 0.003%

    No Known Activations