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

    Neuronpedia

    INDEX
    Explanations

    restaurant table

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    क
    1.02
    ת
    1.02
    лни
    1.01
    सँग
    0.99
    و
    0.98
     exig
    0.96
    т
    0.96
    द
    0.95
    ল
    0.94
    ه
    0.94
    POSITIVE LOGITS
    Ů
    1.02
    ين
    0.88
    GINIA
    0.87
    ักษณะ
    0.86
    ção
    0.84
     concisely
    0.84
    irectional
    0.84
    promotion
    0.83
     waarop
    0.83
    らう
    0.82
    Act Density 0.000%

    No Known Activations