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

    Neuronpedia

    INDEX
    Explanations

    oster

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    �
    -0.08
     začala
    -0.08
    ’ve
    -0.06
     Mun
    -0.06
     bem
    -0.06
    Starting
    -0.06
     Vander
    -0.06
    )-(
    -0.06
    Tan
    -0.06
     Pis
    -0.06
    POSITIVE LOGITS
     MOZ
    0.08
    _cart
    0.06
     आप
    0.06
    (posts
    0.06
     securing
    0.06
    usra
    0.06
    NOT
    0.06
     SEAL
    0.06
     女
    0.06
    NGTH
    0.06
    Act Density 0.003%

    No Known Activations