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

    Neuronpedia

    INDEX
    Explanations

    Hubble

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    toThrow
    -0.08
    �
    -0.07
    ấu
    -0.07
    섁
    -0.07
     back
    -0.07
    酾
    -0.07
    叟
    -0.07
    呣
    -0.07
    ㆍ
    -0.07
     tunes
    -0.07
    POSITIVE LOGITS
    ("""
    0.08
     Macros
    0.07
    richt
    0.07
     =="
    0.07
     Dipl
    0.07
    (engine
    0.07
    imenti
    0.07
    -mediated
    0.07
     Chains
    0.07
    interaction
    0.07
    Act Density 0.003%

    No Known Activations