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

    Neuronpedia

    INDEX
    Explanations

    syntax related to programming models and definitions

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

    model parameters

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    AsUp
    -0.48
    wieś
    -0.45
    rizona
    -0.40
    tune
    -0.39
    romyalgia
    -0.38
    champ
    -0.38
     Yuma
    -0.37
    ęd
    -0.37
    therape
    -0.36
    inform
    -0.36
    POSITIVE LOGITS
    expandindo
    0.62
    tvguidetime
    0.60
    VersionUID
    0.53
    BagConstraints
    0.48
    enumii
    0.47
    BagLayout
    0.47
    interopRequire
    0.45
     '{@
    0.44
    invokeLater
    0.42
    archiviato
    0.42
    Act Density 0.001%

    No Known Activations