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

    Neuronpedia

    INDEX
    Explanations

    to followed by other words

    np_acts-logits-general · gemini-2.5-flash-lite

    infinitive phrases

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    an
    0.75
    ע
    0.65
    ü
    0.63
    മ
    0.56
    ्यांना
    0.55
    ای
    0.55
    ла
    0.54
    와의
    0.54
    ী
    0.54
    ാ
    0.54
    POSITIVE LOGITS
     is
    0.61
     t
    0.59
     l
    0.59
    ।
    0.57
     h
    0.55
     n
    0.55
    ()
    0.54
    .”
    0.54
     r
    0.53
     financeiros
    0.53
    Act Density 0.038%

    No Known Activations