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

    Neuronpedia

    INDEX
    Explanations

    numerical values associated with data or statistics

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

    numbers with suffixes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     épaules
    -0.40
     interpretación
    -0.39
     ואת
    -0.36
     modalités
    -0.32
     transportar
    -0.32
     acompañar
    -0.31
     conservar
    -0.31
    interprétation
    -0.31
     rodillas
    -0.30
     She
    -0.30
    POSITIVE LOGITS
    enumii
    0.84
    <unused23>
    0.82
    <unused68>
    0.82
    <unused3>
    0.82
    <unused16>
    0.82
    <unused41>
    0.82
    <unused43>
    0.82
    <unused14>
    0.82
    [@BOS@]
    0.82
    <unused8>
    0.82
    Act Density 0.081%

    No Known Activations