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

    Neuronpedia

    INDEX
    Explanations

    instances of empty strings or placeholders in the text

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

    preserve

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    RectangleBorder
    -0.69
    principalColumn
    -0.54
     initComponents
    -0.53
    ]")]
    -0.47
    TestingModule
    -0.46
    ⓧ
    -0.43
     CreateTagHelper
    -0.43
    WebServlet
    -0.42
    HasAnnotation
    -0.42
     JpaRepository
    -0.41
    POSITIVE LOGITS
    preserve
    0.79
    httphttps
    0.62
     Preserve
    0.62
     preserve
    0.60
    Preserve
    0.58
     preserved
    0.53
     preserves
    0.52
    ResumeLayout
    0.50
    ibrator
    0.46
    ellido
    0.46
    Act Density 0.000%

    No Known Activations