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

    Neuronpedia

    INDEX
    Explanations

    reasons to choose something

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    0.87
    ատ
    0.58
    ⺀
    0.56
    溲
    0.55
    าส
    0.54
     on
    0.54
    anych
    0.53
    ATED
    0.52
     risque
    0.52
    ITARY
    0.52
    POSITIVE LOGITS
    žel
    0.64
     strainer
    0.60
    śred
    0.57
    𝗖
    0.57
     countertops
    0.56
     strikeouts
    0.56
     flavonoids
    0.55
    čin
    0.55
    rados
    0.55
     algebra
    0.55
    Act Density 0.006%

    No Known Activations