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

    Neuronpedia

    INDEX
    Explanations

    mathematical equals and currency

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    éli
    0.37
    ideon
    0.36
     guineas
    0.36
     fewer
    0.36
     Fewer
    0.36
     dozen
    0.35
     cinéma
    0.35
    ín
    0.35
     φι
    0.34
     Pembroke
    0.34
    POSITIVE LOGITS
     exactly
    0.37
    exactly
    0.35
    Exactly
    0.35
     EXACT
    0.35
     sebesar
    0.35
     exatamente
    0.34
    金額
    0.33
    Quadr
    0.33
    పె
    0.32
    нику
    0.31
    Act Density 0.020%

    No Known Activations