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

    Neuronpedia

    INDEX
    Explanations

    terms related to events and conditions, particularly those with negative connotations or consequences

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

    absence or abundance of states

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ponte
    -0.52
    Cyfarwyddwr
    -0.49
    omla
    -0.49
    habil
    -0.48
    ніципалі
    -0.47
     Normdatei
    -0.46
    isak
    -0.43
    dAtA
    -0.43
    iale
    -0.43
    vena
    -0.43
    POSITIVE LOGITS
    WithError
    0.42
     fraught
    0.38
     INTERESAR
    0.37
     laden
    0.37
     برانيه
    0.36
     loaded
    0.36
     toalha
    0.36
    WithIdentifier
    0.36
    featureID
    0.35
     plentiful
    0.35
    Act Density 0.081%

    No Known Activations