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

    Neuronpedia

    INDEX
    Explanations

    numerical values and measurements

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

    Numerical values

    np_acts-logits-general · gemini-2.0-flash

    numbers and math expressions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     manchas
    -0.32
     secretos
    -0.32
     fallait
    -0.32
     peringkat
    -0.31
     mercancías
    -0.30
     pelbagai
    -0.30
     masas
    -0.30
     compartido
    -0.29
     alimentaria
    -0.29
     computadoras
    -0.29
    POSITIVE LOGITS
    ⟬
    0.94
     للمعارف
    0.93
     autorytatywna
    0.83
    цездатний
    0.77
     متعلقه
    0.76
    <pad>
    0.73
    <unused47>
    0.73
    <unused52>
    0.73
    <unused42>
    0.73
    <unused8>
    0.73
    Act Density 1.103%

    No Known Activations