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

    Neuronpedia

    INDEX
    Explanations

    Google, Forever, Internal, Short, unfolds, imprinted

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     menggunakan
    0.41
     proses
    0.38
    ственное
    0.37
     besar
    0.36
     मजा
    0.35
     USING
    0.35
     terkenal
    0.35
    惩
    0.35
     usando
    0.35
     cepat
    0.35
    POSITIVE LOGITS
    ンジ
    0.40
     deemed
    0.40
     encouraged
    0.39
    COG
    0.38
    ラボ
    0.38
     intrigued
    0.38
    നട
    0.37
     struck
    0.37
    ൊന്നും
    0.37
    CodeableConcept
    0.37
    Act Density 0.000%

    No Known Activations