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

    Neuronpedia

    INDEX
    Explanations

    names of months or associated abbreviations

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

    ju, jan, jal names

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    makeConstraints
    -0.56
     Савезне
    -0.50
    invokeLater
    -0.47
     الاطلاع
    -0.47
    HomeAsUpEnabled
    -0.46
    Haber
    -0.45
     SwitchCompat
    -0.44
    DoubleQuotes
    -0.43
     صوتيه
    -0.43
    terminate
    -0.42
    POSITIVE LOGITS
    ju
    1.32
    jan
    1.09
    jer
    0.91
    jas
    0.83
    jak
    0.83
    jam
    0.82
    jim
    0.81
    jun
    0.79
    jack
    0.78
    jut
    0.78
    Act Density 0.016%

    No Known Activations