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

    Neuronpedia

    INDEX
    Explanations

    key-value pairs in structured data

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     de
    0.50
     Wann
    0.48
     Speaker
    0.47
     So
    0.46
     Okay
    0.46
     In
    0.45
     Houston
    0.45
     De
    0.45
     Ham
    0.45
     poster
    0.45
    POSITIVE LOGITS
    ជា
    0.49
    Version
    0.48
    едера
    0.47
     паліты
    0.44
    UGUST
    0.44
    팍
    0.43
     народу
    0.43
     restarts
    0.43
    luents
    0.42
    쾅
    0.42
    Act Density 0.001%

    No Known Activations