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

    Neuronpedia

    INDEX
    Explanations

    underscores followed by specific words

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    !»
    0.52
     moistened
    0.48
    ueil
    0.47
    )».
    0.46
    parvec
    0.45
     другу
    0.44
    ichloro
    0.44
     увла
    0.44
    ».
    0.43
     प्रेरित
    0.43
    POSITIVE LOGITS
     _,
    0.86
    _,
    0.72
     (_,
    0.64
     _)
    0.62
    (_,
    0.60
     _
    0.59
     d
    0.50
    ,_
    0.49
     r
    0.48
     _;
    0.48
    Act Density 0.039%

    No Known Activations