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

    Neuronpedia

    INDEX
    Explanations

    references to digital recording and management systems

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

    VDR, anywhere, dog, board

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     inilah
    -0.31
     cậu
    -0.30
    henswürdigkeiten
    -0.29
    strstr
    -0.28
    OrBuilder
    -0.28
     gy
    -0.28
     kı
    -0.28
     bubuk
    -0.27
     trasp
    -0.26
    cor
    -0.26
    POSITIVE LOGITS
    +#+
    0.84
    AsUp
    0.81
     surla
    0.73
    rungsseite
    0.73
     Taktlose
    0.65
    <pad>
    0.60
    <unused52>
    0.60
    <unused16>
    0.59
    <unused8>
    0.59
    [@BOS@]
    0.59
    Act Density 0.005%

    No Known Activations