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

    Neuronpedia

    INDEX
    Explanations

    hexadecimal identifiers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    1.70
    druck
    1.34
    >';
    1.27
    🏯
    1.23
    ';"+
    1.20
    "${
    1.18
    >`;
    1.18
    sunline
    1.16
    nesia
    1.16
     cdot
    1.16
    POSITIVE LOGITS
    at
    2.27
    z
    2.25
    ar
    2.20
    os
    2.16
    ou
    2.03
    el
    1.99
    ين
    1.98
    an
    1.94
    ur
    1.93
    as
    1.90
    Act Density 0.032%

    No Known Activations