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

    Neuronpedia

    INDEX
    Explanations

    reasoning behind

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Alert
    0.99
     réalisé
    0.93
     программе
    0.89
     रचा
    0.89
     Правда
    0.87
    ensatz
    0.87
    ことができます
    0.86
     kuid
    0.86
    বিষ
    0.85
    Flavor
    0.85
    POSITIVE LOGITS
     why
    2.76
    why
    2.48
     mengapa
    2.11
     Why
    2.06
     WHY
    2.01
     behind
    2.01
     warum
    1.98
     waarom
    1.94
    WHY
    1.85
    Why
    1.84
    Act Density 0.138%

    No Known Activations