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

    Neuronpedia

    INDEX
    Explanations

    commas and parentheses

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _today
    -0.06
    Bin
    -0.06
    grp
    -0.06
    rive
    -0.06
     worldly
    -0.06
     conveyed
    -0.06
    _statuses
    -0.06
    _uri
    -0.06
    454
    -0.06
    ).↵↵↵
    -0.06
    POSITIVE LOGITS
     MF
    0.07
    atisf
    0.07
     kvinder
    0.07
     aquatic
    0.07
    ="<<
    0.07
    Eigen
    0.07
    _ioctl
    0.06
     Archbishop
    0.06
    [max
    0.06
    �
    0.06
    Act Density 0.047%

    No Known Activations