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

    Neuronpedia

    INDEX
    Explanations

    all the fish

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ולוג
    0.66
     fraught
    0.66
    Although
    0.66
     although
    0.63
    aporte
    0.63
     стану
    0.63
     normalized
    0.62
     целый
    0.62
    normalized
    0.61
    हालांकि
    0.60
    POSITIVE LOGITS
    ക്കും
    0.78
     wünschen
    0.77
     aspectRatio
    0.74
     envolv
    0.71
     irgendwie
    0.70
    蜴
    0.70
    تام
    0.69
    棿
    0.68
     käs
    0.68
    គ្នា
    0.68
    Act Density 0.451%

    No Known Activations