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

    Neuronpedia

    INDEX
    Explanations

    crisis text line number 8

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ＇
    0.94
    女人
    0.93
     멋
    0.91
     도시
    0.90
     satisfy
    0.90
     irgend
    0.88
     섬
    0.86
     burada
    0.85
    도시
    0.85
     seduce
    0.85
    POSITIVE LOGITS
    जीवी
    1.09
    सिद्ध
    1.06
    فاعل
    1.06
    ட்டார்
    1.03
     وف
    1.02
    డియో
    1.00
    äts
    1.00
     Thermodynamic
    0.99
    rexham
    0.99
     disputed
    0.99
    Act Density 0.107%

    No Known Activations