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

    Neuronpedia

    INDEX
    Explanations

    code documentation return values

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     अभाव
    0.65
    Hub
    0.62
    v
    0.61
     hand
    0.59
     Hand
    0.59
    st
    0.59
    ёз
    0.58
     beginning
    0.58
    Sh
    0.58
    Cook
    0.57
    POSITIVE LOGITS
    <unused190>
    0.93
    chyné
    0.93
     festa
    0.92
    GONDOR
    0.90
    <unused1845>
    0.89
    bindingFields
    0.89
     ज्य
    0.89
    <unused1887>
    0.88
    мб
    0.88
     RUDDER
    0.87
    Act Density 0.000%

    No Known Activations