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

    Neuronpedia

    INDEX
    Explanations

    existence of something (there is/are)

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ご了承
    0.59
    ımda
    0.55
     çöze
    0.55
     તેથી
    0.54
    followlike
    0.54
    érez
    0.54
     cataly
    0.53
     تساعد
    0.53
    ни
    0.53
     pratiquer
    0.53
    POSITIVE LOGITS
     is
    0.93
     were
    0.80
    abouts
    0.78
     a
    0.75
    h
    0.71
     was
    0.70
    a
    0.69
     کوئی
    0.68
     had
    0.63
    S
    0.61
    Act Density 0.070%

    No Known Activations