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

    Neuronpedia

    INDEX
    Explanations

    lists and enumerations

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

    listing examples

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     flavour
    -0.41
    pousada
    -0.40
     ligiloj
    -0.40
     jeito
    -0.40
    RUnlock
    -0.38
    RetentionPolicy
    -0.37
    posedge
    -0.37
     detailsNormal
    -0.36
    ensatz
    -0.36
    httphttps
    -0.35
    POSITIVE LOGITS
     include
    0.71
     including
    0.69
     includes
    0.68
    antaranya
    0.66
    including
    0.64
     Include
    0.63
    CppMethod
    0.61
     Including
    0.60
     Includes
    0.59
     incluyendo
    0.59
    Act Density 0.015%

    No Known Activations