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

    Neuronpedia

    INDEX
    Explanations

    whether

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ွမ်း
    0.70
    द्योगिक
    0.67
    iosos
    0.66
     ennemis
    0.66
     అలా
    0.66
    क्षिप्त
    0.65
     ทุก
    0.64
    に合わせて
    0.63
    ziehungs
    0.63
     poblaciones
    0.63
    POSITIVE LOGITS
     whether
    6.17
    whether
    5.59
     Whether
    5.55
    Whether
    5.41
     WHETHER
    4.67
    是否
    4.66
     apakah
    4.15
     是否
    3.96
    是否有
    3.71
    能否
    3.29
    Act Density 0.472%

    No Known Activations