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

    Neuronpedia

    INDEX
    Explanations

    special character sequences or unusual formatting elements in the text

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

    weather forecasts and code

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    oa̍t
    -0.91
    Бахар
    -0.82
    PhysRev
    -0.79
    GEBURTSDATUM
    -0.76
    OGND
    -0.76
    ロウィン
    -0.75
     gynhyrchwyd
    -0.75
    msgTypes
    -0.73
     ब्रेकडाउन
    -0.73
     gyhoeddwyd
    -0.72
    POSITIVE LOGITS
    1
    0.49
    2
    0.40
    0
    0.38
    5
    0.37
    public
    0.36
    S
    0.35
    this
    0.34
    t
    0.34
    3
    0.34
    i
    0.33
    Act Density 0.013%

    No Known Activations