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

    Neuronpedia

    INDEX
    Explanations

    phrases that discuss reasons and explanations for phenomena, particularly those that highlight multifactorial causes

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

    causes, reasons, explanations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    dama
    -0.47
     referrerpolicy
    -0.45
     Seamless
    -0.44
    hael
    -0.44
     Haring
    -0.43
    mappa
    -0.42
     Hust
    -0.41
     fo
    -0.41
     assistenza
    -0.40
    帖最后由
    -0.40
    POSITIVE LOGITS
     factors
    0.53
    factors
    0.47
     Gründe
    0.45
    //
    0.44
     reasons
    0.44
     explanations
    0.41
     factores
    0.41
     fatores
    0.40
     factor
    0.39
    factor
    0.39
    Act Density 0.068%

    No Known Activations