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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "through" and its variations in various contexts

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

    making it through

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    UserManager
    -0.40
    addTab
    -0.38
    忌
    -0.37
     manager
    -0.37
    AddUser
    -0.36
    setSize
    -0.36
    enis
    -0.35
     madd
    -0.35
    nero
    -0.35
     essentially
    -0.35
    POSITIVE LOGITS
     Autorisations
    0.65
    aarrggbb
    0.55
    phosa
    0.53
    localctx
    0.51
     Italijani
    0.50
     kasarigan
    0.49
    MessageWindow
    0.48
    ReusableCell
    0.48
     vastaan
    0.47
     Numerade
    0.47
    Act Density 0.007%

    No Known Activations