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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "again" and variations of "re-" that indicate repetition or restoration

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

    again, continued, new, improvement

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     grains
    -0.45
     appels
    -0.44
     Arcadia
    -0.44
     languages
    -0.43
    contentLoaded
    -0.43
     cons
    -0.42
    eak
    -0.41
    EDEFAULT
    -0.41
     rotations
    -0.40
     Pico
    -0.40
    POSITIVE LOGITS
    AnimationsModule
    0.54
    ⓧ
    0.52
    TagMode
    0.44
    enterOuterAlt
    0.44
    ValueGeneration
    0.40
    nextProps
    0.38
    出版年
    0.38
     demostrar
    0.38
    ResumeLayout
    0.38
    Бахар
    0.37
    Act Density 0.115%

    No Known Activations