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

    Neuronpedia

    INDEX
    Explanations

    expressions of gratitude or positive sentiment

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

    we are convinced or expect

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     հղումներ
    -0.60
     الرياضيه
    -0.60
     myſelf
    -0.60
     ujednoznacz
    -0.59
     itſelf
    -0.56
    下载附件
    -0.56
     Vikipedi
    -0.52
     Verſ
    -0.51
    mybatisplus
    -0.49
    اعمال
    -0.49
    POSITIVE LOGITS
     believe
    0.68
     believes
    0.56
     believed
    0.56
     expectativa
    0.54
     freuen
    0.54
     expected
    0.53
    хьтан
    0.52
     Believe
    0.52
     chose
    0.51
    believe
    0.51
    Act Density 0.011%

    No Known Activations