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

    Neuronpedia

    INDEX
    Explanations

    numeric sequences or data points

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

    hexadecimal numbers and symbols

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    PYX
    -0.57
    +#+#
    -0.56
    Rohy
    -0.52
     Roskov
    -0.51
    ########.
    -0.48
    InjectAttribute
    -0.48
     raiſ
    -0.47
     nakalista
    -0.47
     *++
    -0.47
    Gambas
    -0.46
    POSITIVE LOGITS
    IntoConstraints
    0.50
     acuer
    0.37
     faltan
    0.37
     lógico
    0.36
    NonUser
    0.36
    ském
    0.35
     soñar
    0.35
     négociations
    0.35
     nombreuses
    0.34
     cuesta
    0.33
    Act Density 0.170%

    No Known Activations