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

    Neuronpedia

    INDEX
    Explanations

    select_all action

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     nya
    0.42
    🇷
    0.42
     stalking
    0.40
     підпри
    0.38
     बवाल
    0.38
    企業
    0.38
    వ్య
    0.38
    🗻
    0.38
    ortis
    0.37
    driven
    0.37
    POSITIVE LOGITS
     Latex
    0.46
     LaTeX
    0.46
     Effort
    0.45
     copiar
    0.45
     Expand
    0.44
     Toggle
    0.44
     выполняется
    0.42
    Color
    0.41
    Expand
    0.41
     Shift
    0.41
    Act Density 0.000%

    No Known Activations