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

    Neuronpedia

    INDEX
    Explanations

    numeric values associated with academic citations or references

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

    foreign language identifiers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    GroupLayout
    -0.37
     ready
    -0.35
     Ufer
    -0.33
     vzd
    -0.32
    irci
    -0.32
     uns
    -0.31
    vably
    -0.31
     exact
    -0.31
    ready
    -0.31
     prêt
    -0.31
    POSITIVE LOGITS
     informée
    1.05
     Italijanski
    0.99
     Италијани
    0.88
    ChildScrollView
    0.79
     ivelany
    0.76
    RegressionTest
    0.75
     autorytatywna
    0.75
     ویکی‌پدی
    0.72
    GEBURTSDATUM
    0.71
     Infórmanos
    0.71
    Act Density 0.011%

    No Known Activations