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

    Neuronpedia

    INDEX
    Explanations

    causal conjunctions that introduce reasoning or explanations

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

    introduces explanation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     utafitiHapana
    -0.60
    /*
    -0.54
    :✨
    -0.52
     ujednoznacz
    -0.49
    rungsseite
    -0.48
    ⟭
    -0.48
     uLocal
    -0.47
    󠁴
    -0.47
    irvana
    -0.46
    stateProvider
    -0.45
    POSITIVE LOGITS
    Caches
    0.46
     كومونز
    0.43
    Damit
    0.43
    umably
    0.41
    Erreferentziak
    0.41
    XmlAccessorType
    0.41
    ledem
    0.40
     Damit
    0.40
    ostante
    0.40
    untos
    0.37
    Act Density 0.029%

    No Known Activations