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

    Neuronpedia

    INDEX
    Explanations

    assertive statements and inquiries about expectations and possibilities

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

    if... then consequence

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    يكب
    -0.65
     Normdatei
    -0.60
     للاسماء
    -0.54
     חיצוניים
    -0.54
    httphttps
    -0.54
    ousands
    -0.52
    BagLayout
    -0.52
    fromCharCode
    -0.52
     Gradient
    -0.51
     Virol
    -0.51
    POSITIVE LOGITS
     then
    0.53
     Then
    0.52
    Dann
    0.50
     THEN
    0.46
    Then
    0.45
     Dann
    0.44
    then
    0.44
    Alors
    0.42
    alors
    0.40
     entonces
    0.38
    Act Density 0.059%

    No Known Activations