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

    Neuronpedia

    INDEX
    Explanations

    Say

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ের
    0.64
    say
    0.42
    PLAN
    0.38
    ）,
    0.38
    껐
    0.37
     કહે
    0.37
    sene
    0.37
    ی
    0.37
     covari
    0.36
     कॉमे
    0.36
    POSITIVE LOGITS
     thanks
    0.94
    thanks
    0.89
     Thanks
    0.84
    Thanks
    0.82
    Hi
    0.82
     gracias
    0.80
     grazie
    0.80
     Hi
    0.79
    ings
    0.78
     thank
    0.77
    Act Density 0.002%

    No Known Activations