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

    Neuronpedia

    INDEX
    Explanations

    references to snapshots or related terms in various contexts

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

    snapshot of

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Infórmanos
    -0.41
     erkek
    -0.40
     vym
    -0.39
    ufficio
    -0.38
    Ufficio
    -0.38
     betyder
    -0.38
     feminina
    -0.37
    err
    -0.37
     eikä
    -0.36
     dolayı
    -0.36
    POSITIVE LOGITS
     snapshot
    2.19
     Snapshot
    2.08
    snapshot
    1.95
     snapshots
    1.88
    Snapshot
    1.86
    snapshots
    1.49
    pshots
    1.49
    Snapshots
    1.42
    SNAPSHOT
    1.41
    pshot
    0.96
    Act Density 0.004%

    No Known Activations