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

    Neuronpedia

    INDEX
    Explanations

    and

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     М
    -0.07
     conveyed
    -0.07
    디어
    -0.06
    ोड
    -0.06
    ilton
    -0.06
    stitute
    -0.06
     criter
    -0.06
    'an
    -0.06
    casecmp
    -0.06
     derece
    -0.05
    POSITIVE LOGITS
     ).
    0.08
     IsPlainOldData
    0.07
    ]).
    0.07
    _SELF
    0.07
     Background
    0.07
     root
    0.06
    )").
    0.06
     HomePage
    0.06
     Rename
    0.06
     commissioned
    0.06
    Act Density 0.048%

    No Known Activations