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

    Neuronpedia

    INDEX
    Explanations

    applying formulas and rules

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Determine
    0.50
    Simplify
    0.47
    determine
    0.44
     Determine
    0.44
     determine
    0.42
    simplify
    0.42
     понять
    0.42
     simplify
    0.42
     expressions
    0.41
    Equations
    0.41
    POSITIVE LOGITS
     applying
    0.59
     aplicando
    0.54
     Applying
    0.54
     Applied
    0.52
    applying
    0.50
     referring
    0.49
     doing
    0.48
    Applied
    0.47
     aplic
    0.46
     applied
    0.46
    Act Density 0.053%

    No Known Activations