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

    Neuronpedia

    INDEX
    Explanations

    attributes related to text styling and formatting in a code context

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

    user prompt

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     rumbo
    -0.40
     yyr
    -0.40
    ={};
    -0.39
     Niedersch
    -0.39
    ('/');
    -0.37
    ManyToOne
    -0.37
    insatz
    -0.37
     ganchillo
    -0.36
    ("/");
    -0.36
    šanās
    -0.36
    POSITIVE LOGITS
    adaptiveStyles
    0.63
    OGND
    0.59
    principalColumn
    0.58
     MainAxisSize
    0.57
     FetchType
    0.57
     للمعارف
    0.53
     صوتيه
    0.52
    ьаж
    0.50
    ValueStyle
    0.50
    QMetaType
    0.49
    Act Density 0.000%

    No Known Activations