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

    Neuronpedia

    INDEX
    Explanations

    cavalry

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    じゃ
    -0.07
    edula
    -0.07
    28
    -0.07
    ung
    -0.07
    屋
    -0.06
    UILabel
    -0.06
     economies
    -0.06
     firewall
    -0.06
    ему
    -0.06
    imeter
    -0.06
    POSITIVE LOGITS
     cavalry
    0.11
     Caval
    0.08
    (contract
    0.06
    ↵↵↵↵↵↵↵↵↵
    0.06
     surprises
    0.06
     музы
    0.06
     عش
    0.06
     unconventional
    0.06
     constituted
    0.06
     thanked
    0.06
    Act Density 0.003%

    No Known Activations