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

    Neuronpedia

    INDEX
    Explanations

    want ingredient response learner cases

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    𝓵
    1.12
     Xcode
    1.08
    ateur
    1.05
    此之外
    1.03
     hi
    1.01
     Hi
    1.00
     vidrio
    0.98
    𝒆
    0.98
     eum
    0.98
    Ｑ
    0.98
    POSITIVE LOGITS
    엡
    1.31
    wss
    1.24
    ାର
    1.23
    Purs
    1.23
     उर्वर
    1.22
     स्वयं
    1.16
     צריך
    1.16
    삽
    1.16
     महंगी
    1.14
     breve
    1.14
    Act Density 0.000%

    No Known Activations