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

    Neuronpedia

    INDEX
    Explanations

    contrasting conjunctions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    jų
    0.43
     empate
    0.41
    ília
    0.40
    Ῥ
    0.39
    オフ
    0.38
     的
    0.38
    रा
    0.38
     être
    0.38
    +"
    0.38
    _
    0.38
    POSITIVE LOGITS
     but
    0.53
     although
    0.53
    but
    0.50
     ಆದರೆ
    0.46
     with
    0.46
    and
    0.45
     Although
    0.45
     especially
    0.45
     though
    0.44
     aunque
    0.44
    Act Density 0.002%

    No Known Activations