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

    Neuronpedia

    INDEX
    Explanations

    phrases that indicate effects, descriptions, or results in relation to various subjects

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

    This is

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ſtand
    -0.51
    jspb
    -0.49
    bitField
    -0.48
     الرياضيه
    -0.48
     ſch
    -0.47
     myſelf
    -0.45
    BeanUtils
    -0.42
     raiſ
    -0.41
     uſed
    -0.41
     groet
    -0.40
    POSITIVE LOGITS
     Esto
    0.52
    Esto
    0.47
    ')));
    0.46
    tamment
    0.44
    これが
    0.42
    cupertino
    0.41
    ")));
    0.41
     للاسماء
    0.40
    これは
    0.39
    aternion
    0.38
    Act Density 0.481%

    No Known Activations