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

    Neuronpedia

    INDEX
    Explanations

    important statements or conclusions within a text

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

    contrast and consequence

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     pri
    -0.44
     pic
    -0.43
    —
    -0.38
    RegressionTest
    -0.37
    endfor
    -0.37
     residents
    -0.36
    ann
    -0.34
    реса
    -0.34
    miro
    -0.33
    Bioaccumulative
    -0.33
    POSITIVE LOGITS
     vergeten
    0.63
     propOrder
    0.60
     ujednoznacz
    0.59
    genodigd
    0.53
    SourceChecksum
    0.52
    不夠
    0.51
     telefoon
    0.48
     kekurangan
    0.48
     resourceCulture
    0.48
     kesulitan
    0.47
    Act Density 0.349%

    No Known Activations