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

    Neuronpedia

    INDEX
    Explanations

    seems or appears

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     inilah
    0.72
     deoarece
    0.72
    brev
    0.72
     därför
    0.68
     personale
    0.68
     pensée
    0.67
    髓
    0.67
     tabulation
    0.66
     خودم
    0.66
    orest
    0.65
    POSITIVE LOGITS
     seems
    2.35
     seem
    2.34
     seemed
    2.20
    seems
    1.82
     seeming
    1.80
     Seems
    1.76
     appears
    1.75
    似乎
    1.74
    Seems
    1.65
     appear
    1.64
    Act Density 0.363%

    No Known Activations