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

    Neuronpedia

    INDEX
    Explanations

    those those those

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     silence
    0.84
    Silent
    0.78
     Silent
    0.77
    癢
    0.75
     noisy
    0.73
     taxe
    0.73
    Silence
    0.72
     Mathemat
    0.72
    Topic
    0.71
     towels
    0.71
    POSITIVE LOGITS
    那些
    0.63
    sco
    0.60
     Those
    0.59
    Those
    0.58
    anging
    0.57
     those
    0.56
    んと
    0.55
    aysa
    0.54
    anto
    0.54
    anged
    0.54
    Act Density 0.098%

    No Known Activations