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

    Neuronpedia

    INDEX
    Explanations

    there followed by being verbs

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     করিনি
    0.75
    に加え
    0.73
    LET
    0.70
    何况
    0.70
    그리고
    0.69
     Marketing
    0.68
    ഹ്ലാ
    0.68
     поверну
    0.67
    さて
    0.66
    ージャ
    0.65
    POSITIVE LOGITS
     are
    2.19
     is
    1.96
     exists
    1.80
     isn
    1.61
     aren
    1.56
    abouts
    1.53
     jsou
    1.51
     sont
    1.44
     seems
    1.40
     were
    1.40
    Act Density 0.255%

    No Known Activations