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

    Neuronpedia

    INDEX
    Explanations

    design or code

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     stunned
    0.38
    था
    0.37
    ➣
    0.37
    gar
    0.36
     muszą
    0.36
     huge
    0.36
     séptimo
    0.36
    嫒
    0.36
     glam
    0.36
     animator
    0.36
    POSITIVE LOGITS
     Quotient
    0.45
     reflections
    0.41
     Tree
    0.41
    istical
    0.41
    疇
    0.39
     Tip
    0.38
     Quantitative
    0.38
    ToolTip
    0.38
     Flexibility
    0.37
    ګه
    0.37
    Act Density 0.000%

    No Known Activations