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

    Neuronpedia

    INDEX
    Explanations

    mathematical symbols and operators

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

    mathematical notation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     combined
    -0.39
    entuh
    -0.38
     <=",
    -0.37
    VYMaps
    -0.36
     magnets
    -0.36
    -0.36
     EnglishChoose
    -0.35
     mixed
    -0.35
    hoeddwyd
    -0.35
    adpleegd
    -0.34
    POSITIVE LOGITS
    0.61
    foria
    0.57
    casio
    0.56
    coltura
    0.55
     informée
    0.54
    ſelves
    0.53
     MainAxisSize
    0.53
    大家好
    0.53
    ainville
    0.51
    chengladbach
    0.51
    Act Density 0.303%

    No Known Activations