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

    Neuronpedia

    INDEX
    Explanations

    101

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    coma
    0.45
    module
    0.44
     Regan
    0.39
     module
    0.39
    figuration
    0.38
    stru
    0.37
     Appellant
    0.37
     ~(~)
    0.37
     `>=`,
    0.36
    retrieve
    0.36
    POSITIVE LOGITS
     спосо
    0.48
     maneras
    0.48
    Ways
    0.46
     things
    0.46
    Things
    0.46
     cosas
    0.45
     ways
    0.44
     طرق
    0.43
     способы
    0.43
     चीजें
    0.43
    Act Density 0.002%

    No Known Activations