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

    Neuronpedia

    INDEX
    Explanations

    import (package/class)

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     应用
    0.46
    㸸
    0.43
    forName
    0.43
    嘧
    0.39
    ViewGroup
    0.38
     fruto
    0.38
    腈
    0.37
     application
    0.36
     యూని
    0.36
    UNI
    0.35
    POSITIVE LOGITS
     jakarta
    0.48
     jak
    0.43
    reactor
    0.42
    wedd
    0.41
    pros
    0.39
    jakarta
    0.39
    jak
    0.39
    gtrsim
    0.38
     Sardar
    0.38
    kat
    0.37
    Act Density 0.001%

    No Known Activations