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

    Neuronpedia

    INDEX
    Explanations

    common abbreviations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    oy
    0.50
     Viceroy
    0.47
     Yangzhou
    0.46
     ionizing
    0.46
     Negev
    0.45
     Terminator
    0.45
     SUVs
    0.44
    涓
    0.44
     HEK
    0.44
     Δε
    0.44
    POSITIVE LOGITS
     scrive
    0.46
     setObject
    0.46
     thumb
    0.44
     almış
    0.43
    腦
    0.43
     glaube
    0.42
    写作
    0.41
    边的
    0.40
    codigo
    0.39
     out
    0.39
    Act Density 0.000%

    No Known Activations