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

    Neuronpedia

    INDEX
    Explanations

    number formatting

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     -------
    -0.08
    MOV
    -0.07
    919
    -0.07
     capsules
    -0.07
    侍
    -0.07
    ENTRY
    -0.07
    _ATTRIBUTES
    -0.07
    ΙΚΗΣ
    -0.06
    秋
    -0.06
    _KERNEL
    -0.06
    POSITIVE LOGITS
     ця
    0.06
    _ment
    0.06
     пара
    0.06
    カ
    0.06
     ue
    0.06
    -command
    0.06
     pretend
    0.06
    _GT
    0.06
     nl
    0.06
     rubbish
    0.05
    Act Density 0.003%

    No Known Activations