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

    Neuronpedia

    INDEX
    Explanations

    numerical values and programming constructs

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

    numbers and code snippets

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    webdriver
    -0.29
    后
    -0.28
    Då
    -0.28
     Defensa
    -0.28
    laszt
    -0.28
    állítás
    -0.27
     Formación
    -0.27
     expériment
    -0.26
     transparencia
    -0.26
     asistencia
    -0.26
    POSITIVE LOGITS
    enderror
    0.82
     queſta
    0.75
    ModelSerializer
    0.68
     /\.(
    0.66
     maxn
    0.66
     FetchType
    0.66
    msgTypes
    0.65
     Infórmanos
    0.64
    SharedDtor
    0.64
    <unused23>
    0.63
    Act Density 0.030%

    No Known Activations