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

    Neuronpedia

    INDEX
    Explanations

    the + specific nouns

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Grande
    0.78
    go
    0.75
    IX
    0.73
    beef
    0.73
    hay
    0.71
     profundo
    0.70
     persegu
    0.70
     Grande
    0.68
    ix
    0.67
    Opt
    0.66
    POSITIVE LOGITS
     items
    0.79
     facts
    0.76
     products
    0.74
     configuration
    0.73
     them
    0.73
    کری
    0.73
     entries
    0.73
     modified
    0.73
     descriptive
    0.72
     모습
    0.72
    Act Density 0.459%

    No Known Activations