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

    Neuronpedia

    INDEX
    Explanations

    gerunds and ongoing actions in sentences

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

    stopping actions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    RouterModule
    -0.40
    addPreferredGap
    -0.40
    Ditto
    -0.38
    AnchorStyles
    -0.37
    )");
    -0.36
    Predecesor
    -0.36
    دانشنامهٔ
    -0.35
     barnen
    -0.35
    ungeon
    -0.34
    listdir
    -0.34
    POSITIVE LOGITS
     Stop
    0.68
    Stop
    0.62
     stopped
    0.59
     STOP
    0.58
    STOP
    0.57
    stop
    0.57
    Stopped
    0.57
     Stopped
    0.56
     stop
    0.56
    stopped
    0.54
    Act Density 0.021%

    No Known Activations