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

    Neuronpedia

    INDEX
    Explanations

    issues related to programming or software errors and their solutions

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

    "work" or "worked"

    np_acts-logits-general · gemini-2.0-flash

    whether or not things work

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    UrlResolution
    -0.75
    脚注の使い方
    -0.71
    ValueGenerated
    -0.65
     saites
    -0.64
     Offisielt
    -0.64
     typelib
    -0.64
    mybatisplus
    -0.63
    Síguenos
    -0.62
    SharedDtor
    -0.61
    UpInside
    -0.61
    POSITIVE LOGITS
     works
    2.53
     worked
    2.51
     Worked
    2.15
     Works
    2.13
    worked
    2.13
    Works
    2.08
    Worked
    2.07
     WORKS
    2.06
    works
    2.03
     working
    1.97
    Act Density 0.696%

    No Known Activations