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

    Neuronpedia

    INDEX
    Explanations

    consider user experience

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     huyện
    0.52
    ibank
    0.51
     bật
    0.49
     gjør
    0.47
     książ
    0.47
    ̣ng
    0.46
    gever
    0.46
    ibor
    0.46
     gamle
    0.45
     bombas
    0.45
    POSITIVE LOGITS
    Pod
    0.48
    TS
    0.47
    Natural
    0.47
    Spanish
    0.47
    Smart
    0.46
    NS
    0.46
    SL
    0.44
    ES
    0.43
    STR
    0.43
    LS
    0.43
    Act Density 0.002%

    No Known Activations