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

    Neuronpedia

    INDEX
    Explanations

    fitting and proper

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    狷
    0.83
     anormal
    0.80
     astron
    0.80
     égard
    0.78
     راز
    0.78
     acutely
    0.78
    𝘻
    0.77
    zelfde
    0.77
    фект
    0.75
     విషయం
    0.74
    POSITIVE LOGITS
    ractical
    0.68
    മ്പോൾ
    0.68
    彝
    0.65
     pel
    0.65
     sesuai
    0.64
    appropri
    0.62
     CryptoJS
    0.61
     meng
    0.60
    ണ്ഡി
    0.60
     отме
    0.59
    Act Density 0.001%

    No Known Activations