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

    Neuronpedia

    INDEX
    Explanations

    grouping and prediction

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     एवरी
    0.47
     اجيب
    0.46
     consegn
    0.46
     météor
    0.45
     സ്വന്ത
    0.44
     extravagance
    0.44
    ಚ್
    0.44
     germinate
    0.44
     attractiveness
    0.43
     groei
    0.42
    POSITIVE LOGITS
    v
    0.46
    sa
    0.46
    anch
    0.39
    prob
    0.39
    por
    0.38
    ai
    0.38
     porches
    0.38
        
    0.37
    Theatre
    0.37
    ll
    0.37
    Act Density 0.001%

    No Known Activations