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

    Neuronpedia

    INDEX
    Explanations

    closing parenthesis 3

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    council
    0.42
    rospection
    0.40
    municipal
    0.40
    billing
    0.40
    ranath
    0.39
    三年
    0.39
     thème
    0.39
     ಮಾರ
    0.39
    SHARED
    0.39
    pour
    0.38
    POSITIVE LOGITS
    Transform
    0.39
     Transform
    0.38
    കൃ
    0.35
    كرة
    0.35
    想像
    0.34
    放
    0.34
    Anal
    0.34
    Remember
    0.34
    Раз
    0.34
     Overs
    0.34
    Act Density 0.001%

    No Known Activations