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

    Neuronpedia

    INDEX
    Explanations

    methods and attributes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     getCurrent
    0.46
     getState
    0.43
     এইরূপে
    0.42
    getCurrent
    0.40
     getString
    0.40
     precepts
    0.40
     stabilizes
    0.39
     traduce
    0.39
     fetchData
    0.39
    signIn
    0.39
    POSITIVE LOGITS
     old
    0.39
    w
    0.36
    ть
    0.35
    ów
    0.35
     Old
    0.35
     OLD
    0.35
    ಧ
    0.35
    β
    0.34
     EMB
    0.34
    mene
    0.34
    Act Density 0.005%

    No Known Activations