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

    Neuronpedia

    INDEX
    Explanations

    defendant manifested

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    जेक्शन
    0.49
     يك
    0.49
     समझाया
    0.49
    adás
    0.46
     explique
    0.45
    ată
    0.44
    Dic
    0.44
    日子
    0.43
    мени
    0.42
    дите
    0.42
    POSITIVE LOGITS
     เพียง
    0.48
     decline
    0.48
     brom
    0.47
     landscaped
    0.46
    ?
    0.45
     scur
    0.42
     rumen
    0.42
     parlor
    0.42
     grouse
    0.41
     jaundice
    0.41
    Act Density 0.001%

    No Known Activations