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

    Neuronpedia

    INDEX
    Explanations

    expressions related to careful consideration and personal emotional investment

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

    adverbs modifying verbs or adjectives

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    gate
    -0.56
    gwt
    -0.52
     Har
    -0.51
     *)&
    -0.50
     trans
    -0.50
    spreading
    -0.50
     W
    -0.49
     Cat
    -0.48
     dados
    -0.48
     indis
    -0.47
    POSITIVE LOGITS
     EconPapers
    0.88
    TestingModule
    0.85
    曖昧さ回避
    0.84
     Administrativna
    0.78
    PerformLayout
    0.76
    ContentAsync
    0.75
     мәкал
    0.74
    ConstraintMaker
    0.74
     itſelf
    0.70
    DoubleQuotes
    0.68
    Act Density 0.144%

    No Known Activations