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

    Neuronpedia

    INDEX
    Explanations

    tap

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    zech
    -0.06
    emek
    -0.06
     радян
    -0.06
     Wang
    -0.06
    赏
    -0.06
     Shutdown
    -0.06
    飯
    -0.06
     svých
    -0.06
     plaisir
    -0.06
     monument
    -0.06
    POSITIVE LOGITS
     elbows
    0.07
     disclosures
    0.07
    926
    0.07
    -posts
    0.07
    _va
    0.06
     addictive
    0.06
    _repr
    0.06
     scares
    0.06
     різ
    0.06
     клас
    0.06
    Act Density 0.005%

    No Known Activations