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

    Neuronpedia

    INDEX
    Explanations

    Yes, I’m here

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     высокий
    0.74
     höhere
    0.71
    高い
    0.70
    Happy
    0.70
     HAPPY
    0.70
     savoir
    0.69
     വലിയ
    0.69
     darin
    0.69
    steiger
    0.69
     Happy
    0.68
    POSITIVE LOGITS
     Prefer
    0.75
     prefer
    0.70
    pected
    0.69
    ely
    0.68
    LiveData
    0.67
    нес
    0.66
    ūk
    0.66
    бли
    0.66
    Нор
    0.65
    Prefer
    0.65
    Act Density 0.000%

    No Known Activations