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

    Neuronpedia

    INDEX
    Explanations

    Flask

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     playoffs
    -0.08
     Indian
    -0.07
    -bound
    -0.07
    _player
    -0.07
    Los
    -0.07
    .paint
    -0.07
    has
    -0.07
    _WEAPON
    -0.06
     Phase
    -0.06
     phase
    -0.06
    POSITIVE LOGITS
     PQ
    0.07
     гриб
    0.07
     удов
    0.06
    #=
    0.06
    icaret
    0.06
    _example
    0.06
     nilai
    0.06
    judul
    0.06
    )):
↵
    0.06
    .Anchor
    0.06
    Act Density 0.000%

    No Known Activations