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

    Neuronpedia

    INDEX
    Explanations

    level of

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     कढ़ाई
    0.78
    ódigo
    0.76
     JVM
    0.71
     Debido
    0.71
     veik
    0.70
     mortars
    0.69
    ător
    0.69
    нді
    0.69
    잡
    0.69
    नोई
    0.69
    POSITIVE LOGITS
     what
    0.69
    ob
    0.64
     What
    0.64
    entropy
    0.61
     degré
    0.58
    毒
    0.58
     grave
    0.57
     effort
    0.57
     antiseptic
    0.56
     శు
    0.56
    Act Density 0.075%

    No Known Activations