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

    Neuronpedia

    INDEX
    Explanations

    would you like

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Wouldn
    0.82
    Would
    0.75
     Would
    0.72
     genetics
    0.72
     sarebbe
    0.71
     wouldn
    0.67
     Wouldn
    0.67
     repentance
    0.66
     would
    0.66
    would
    0.66
    POSITIVE LOGITS
     lik
    0.80
     like
    0.79
    like
    0.75
     ike
    0.75
    Like
    0.75
     Like
    0.70
    LIKE
    0.66
    ike
    0.65
     लाइक
    0.62
     holde
    0.61
    Act Density 0.129%

    No Known Activations