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

    Neuronpedia

    INDEX
    Explanations

    phrases related to meetings and interpersonal interactions

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

    prepositions before nouns and verbs

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     occaf
    -0.45
    لينكات
    -0.36
    â
    -0.35
     poffe
    -0.35
     occafion
    -0.34
    llte
    -0.33
     stir
    -0.33
     whofe
    -0.32
    Exclusion
    -0.32
     привести
    -0.32
    POSITIVE LOGITS
     Bewußt
    0.68
     resourceCulture
    0.60
    0.57
     desmotivaciones
    0.54
    fromnode
    0.54
     verksam
    0.51
     vocês
    0.50
    はじめに
    0.49
    RUnlock
    0.49
    ranath
    0.49
    Act Density 0.301%

    No Known Activations