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

    Neuronpedia

    INDEX
    Explanations

    numerical values and their associated scientific or mathematical context

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

    numbers and units

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     raiſ
    -0.41
     feroit
    -0.39
     pouvoit
    -0.39
     auroit
    -0.39
     juſ
    -0.38
     تانيه
    -0.38
     pleaſure
    -0.38
    izioni
    -0.38
     spéciaux
    -0.36
     Græ
    -0.35
    POSITIVE LOGITS
    ValueStyle
    0.70
    DIPSETTING
    0.58
     CreateTagHelper
    0.58
     незавершена
    0.57
    AndEndTag
    0.56
    ResumeLayout
    0.52
    تقاوى
    0.51
     Chwiliwch
    0.48
     صوتيه
    0.47
    رشف
    0.47
    Act Density 0.314%

    No Known Activations