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

    Neuronpedia

    INDEX
    Explanations

    abrasive detective

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ात
    1.00
     отде
    0.97
    retto
    0.96
    fü
    0.94
    remain
    0.93
     MAL
    0.92
     счет
    0.92
    TRE
    0.91
    techn
    0.91
     наме
    0.89
    POSITIVE LOGITS
     provoque
    1.22
     buf
    1.10
     apaixon
    1.10
     apoptosis
    1.06
    डे
    1.06
    ÇÃO
    1.02
     iria
    1.02
     যেন
    1.00
    过程中
    1.00
     sop
    0.99
    Act Density 0.000%

    No Known Activations