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

    Neuronpedia

    INDEX
    Explanations

    references to snapshots or instances in various contexts

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

    snapshot, snapshot versions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    i
    -0.45
    if
    -0.45
    3
    -0.43
    err
    -0.42
    I
    -0.41
    ufficio
    -0.41
    E
    -0.41
    Ufficio
    -0.39
     між
    -0.36
    F
    -0.36
    POSITIVE LOGITS
     Snapshot
    1.47
     snapshot
    1.44
    snapshot
    1.34
    Snapshot
    1.34
     snapshots
    1.22
    pshots
    1.15
    Snapshots
    1.02
    snapshots
    1.02
    SNAPSHOT
    0.98
     dataSnapshot
    0.93
    Act Density 0.005%

    No Known Activations