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

    Neuronpedia

    INDEX
    Explanations

    web addresses and domains

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

    site addresses with slashes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     незавершена
    -0.52
     niebla
    -0.47
     tartalomajánló
    -0.47
     Comprometido
    -0.45
     Signalez
    -0.43
     Kindheit
    -0.42
     ángeles
    -0.40
     Encuentra
    -0.40
    ปัญ
    -0.40
     desierto
    -0.39
    POSITIVE LOGITS
    InstrumentedTest
    0.59
    com
    0.56
    ftagPool
    0.56
     com
    0.55
    endregion
    0.54
    ագրություններ
    0.54
    COM
    0.53
    コム
    0.52
     ujednoznacz
    0.51
    endphp
    0.50
    Act Density 0.056%

    No Known Activations