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

    Neuronpedia

    INDEX
    Explanations

    technical terms and concepts related to scientific or mathematical descriptions

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

    Mathematical or physics-related expressions

    np_acts-logits-general · gemini-2.0-flash

    position to position

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ante
    -0.49
     shudder
    -0.48
    bili
    -0.46
    masta
    -0.45
    Misty
    -0.44
    holl
    -0.44
    kira
    -0.43
     tr
    -0.43
    strukturen
    -0.43
    êtes
    -0.43
    POSITIVE LOGITS
     doubtnut
    0.79
     Lordships
    0.77
    AndEndTag
    0.70
     useStyles
    0.69
    AddTagHelper
    0.69
     Monfieur
    0.66
     محفوظة
    0.66
     feroit
    0.65
     ainfi
    0.64
     iſt
    0.64
    Act Density 0.349%

    No Known Activations