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

    Neuronpedia

    INDEX
    Explanations

    visual hierarchy and flow

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    пил
    0.39
     σχετικά
    0.38
     unassuming
    0.38
    ALTERNATIVNAMEN
    0.38
    ਟ
    0.37
    ял
    0.36
     accolades
    0.35
    placeholder
    0.35
     መሳሪያ
    0.34
     শহরে
    0.34
    POSITIVE LOGITS
     offered
    0.43
     ignite
    0.41
     naked
    0.39
     offer
    0.39
     instit
    0.38
     nominated
    0.38
    Offer
    0.38
    囲
    0.38
     oferecer
    0.37
    Ofer
    0.37
    Act Density 0.001%

    No Known Activations