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

    Neuronpedia

    INDEX
    Explanations

    phrases or structures that denote criteria or categorizations within a given context

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

    list items/criteria

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ↵
    -0.32
     doc
    -0.30
     Arrange
    -0.29
    ↵↵
    -0.29
     fil
    -0.29
     Sha
    -0.27
     arrange
    -0.27
    annotate
    -0.27
     leave
    -0.26
     bis
    -0.26
    POSITIVE LOGITS
    IntoConstraints
    0.81
     Normdatei
    0.79
     ujednoznacz
    0.76
     initComponents
    0.75
    rungsseite
    0.75
     estekak
    0.72
    cipais
    0.71
    Personendaten
    0.70
     ivelany
    0.67
     мәкал
    0.66
    Act Density 0.065%

    No Known Activations