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

    Neuronpedia

    INDEX
    Explanations

    return statements

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Alk
    0.58
    Inflation
    0.58
    LONDON
    0.54
    ĵo
    0.54
    Storia
    0.53
    ΤΟ
    0.53
    ΕΙ
    0.53
    Rome
    0.52
    Johannes
    0.51
    Els
    0.51
    POSITIVE LOGITS
    //
    0.60
     //
    0.58
     Greenway
    0.55
     /*
    0.54
     reduce
    0.50
     economic
    0.50
     return
    0.50
    ự
    0.50
     }
    0.50
     â
    0.48
    Act Density 0.552%

    No Known Activations