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

    Neuronpedia

    INDEX
    Explanations

    Bal

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Hermione
    -0.07
     tp
    -0.07
     pans
    -0.07
    ᑐ
    -0.07
     ns
    -0.07
     quest
    -0.07
     chơi
    -0.07
     worth
    -0.06
    emade
    -0.06
    بن
    -0.06
    POSITIVE LOGITS
     nije
    0.08
     RouteServiceProvider
    0.08
    _band
    0.07
     positives
    0.07
     decoding
    0.07
    ographer
    0.07
    EncodingException
    0.07
    移民
    0.07
     לפנות
    0.07
     hashing
    0.07
    Act Density 0.003%

    No Known Activations