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

    Neuronpedia

    INDEX
    Explanations

    specific word meanings

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     binding
    0.41
     biodegrad
    0.41
     seemingly
    0.40
     bindings
    0.39
     streamer
    0.38
     extens
    0.38
     Binding
    0.38
    一套
    0.38
     niet
    0.37
    ەیە
    0.37
    POSITIVE LOGITS
    WART
    0.54
    ATH
    0.48
    ATHER
    0.47
    kari
    0.46
    wy
    0.46
    A
    0.46
    ഗ
    0.46
    ktr
    0.43
    mon
    0.43
    ﻊ
    0.42
    Act Density 0.003%

    No Known Activations