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

    Neuronpedia

    INDEX
    Explanations

    references to shared resources and collaboration

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    shared resources

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    SourceChecksum
    -0.46
     Mahar
    -0.40
    AKU
    -0.38
     Retention
    -0.38
    rig
    -0.38
    FromDB
    -0.38
    itesse
    -0.37
     Livre
    -0.37
    jíma
    -0.37
     rig
    -0.37
    POSITIVE LOGITS
     shared
    0.85
     compartido
    0.77
    shared
    0.73
     Shared
    0.65
    Shared
    0.65
    aarrggbb
    0.62
     compartil
    0.60
     compartió
    0.60
     sharing
    0.60
     compartida
    0.60
    Act Density 0.292%

    No Known Activations