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

    Neuronpedia

    INDEX
    Explanations

    cultural sensitivities and input

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Tether
    0.42
     Interpret
    0.41
    m
    0.41
     See
    0.40
     Vent
    0.40
     συνεχ
    0.40
     Void
    0.39
     Prist
    0.39
     Through
    0.39
     Priority
    0.39
    POSITIVE LOGITS
     हानि
    0.50
    ᱝ
    0.48
     पढ़ाई
    0.48
     ક્ષ
    0.47
    고사
    0.46
    った
    0.46
    гән
    0.46
    マイ
    0.45
    нул
    0.45
    ју
    0.45
    Act Density 0.001%

    No Known Activations