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

    Neuronpedia

    INDEX
    Explanations

    adverbs that indicate the degree of performance or efficiency

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    how well something is done

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    localctx
    -0.55
    TemporalType
    -0.53
    adaptiveStyles
    -0.49
    BITDA
    -0.49
    WithIOException
    -0.48
    在她
    -0.45
    RectangleBorder
    -0.44
    ânsito
    -0.43
    在他
    -0.43
    arakhand
    -0.42
    POSITIVE LOGITS
     they
    0.81
     we
    0.77
     you
    0.60
     she
    0.54
    they
    0.52
     he
    0.52
     someone
    0.51
     it
    0.51
    we
    0.47
    certain
    0.46
    Act Density 0.011%

    No Known Activations