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

    Neuronpedia

    INDEX
    Explanations

    a or b variable assignment

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    های
    0.60
    ị
    0.57
    および
    0.54
    lose
    0.53
    ס
    0.52
     राजस्व
    0.51
    ロ
    0.51
     двер
    0.50
    Rejected
    0.49
    вшие
    0.49
    POSITIVE LOGITS
     daycare
    0.74
    eka
    0.71
    ânia
    0.68
     rahat
    0.68
     CHANGE
    0.67
     cyberspace
    0.67
    adır
    0.67
    agaan
    0.66
     حافظ
    0.65
    0.65
    Act Density 0.001%

    No Known Activations