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

    Neuronpedia

    INDEX
    Explanations

    references to specific brands or force-related terms

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

    force and coercion

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    PreInfinity
    -0.45
    EditorGUILayout
    -0.40
     Compostela
    -0.39
     Elizabethan
    -0.39
    expandindo
    -0.38
    ReusableCell
    -0.37
    OCCURRED
    -0.37
    marginHorizontal
    -0.36
     Domenico
    -0.35
    ngdoc
    -0.35
    POSITIVE LOGITS
    force
    0.92
     Force
    0.88
     force
    0.88
    Force
    0.84
     FORCE
    0.82
    FORCE
    0.77
    Strength
    0.68
     Forces
    0.68
     Strength
    0.67
     Fuerza
    0.66
    Act Density 0.018%

    No Known Activations