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

    Neuronpedia

    INDEX
    Explanations

    website names like Murf.ai

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     bot
    0.62
    媽媽
    0.59
     Mother
    0.57
    allah
    0.56
     mother
    0.55
    坊
    0.54
    bote
    0.54
    काल
    0.54
     Mama
    0.54
     MAS
    0.54
    POSITIVE LOGITS
     Gori
    0.64
    Пор
    0.63
    ânica
    0.62
    Anchor
    0.62
    ánica
    0.62
     swept
    0.62
     Anchor
    0.61
    趸
    0.59
    नन
    0.59
     अंग
    0.58
    Act Density 0.178%

    No Known Activations