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

    Neuronpedia

    INDEX
    Explanations

    programming code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     biệt
    -0.06
    �
    -0.06
     Dropout
    -0.06
    NotAllowed
    -0.06
     jpeg
    -0.06
    cidade
    -0.06
    WithData
    -0.05
     Remain
    -0.05
    hotel
    -0.05
    crew
    -0.05
    POSITIVE LOGITS
     strand
    0.07
     (/
    0.07
    organized
    0.06
    ellschaft
    0.06
     SH
    0.06
    ΟΔ
    0.06
    핑
    0.06
    _Space
    0.06
    Alle
    0.06
    ermo
    0.06
    Act Density 0.001%

    No Known Activations