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

    Neuronpedia

    INDEX
    Explanations

    connecting phrases and references to actions involving relationships or interactions

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

    in that it

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    extAlignment
    -0.55
     للاسماء
    -0.55
    SpringRunner
    -0.52
    存于互联网档案馆
    -0.51
    CodedInputStream
    -0.48
    Попис
    -0.48
    AnimationsModule
    -0.46
    migrationBuilder
    -0.45
     olympiques
    -0.44
    ctu
    -0.44
    POSITIVE LOGITS
     alça
    0.47
     poveznice
    0.45
     puisqu
    0.44
     hiszen
    0.44
     essendo
    0.42
     esser
    0.40
    ">//
    0.38
     avendo
    0.38
    onomía
    0.37
    laszt
    0.37
    Act Density 0.098%

    No Known Activations