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

    Neuronpedia

    INDEX
    Explanations

    data

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    GRA
    -0.07
    (pk
    -0.06
    .rate
    -0.06
    _permission
    -0.06
    ('=
    -0.06
    elve
    -0.06
    .hide
    -0.06
     offsetof
    -0.06
    ]._
    -0.06
    акс
    -0.06
    POSITIVE LOGITS
    mast
    0.07
     팀
    0.07
     overseas
    0.06
     feasible
    0.06
     naveg
    0.06
     USED
    0.06
     needles
    0.06
     Midi
    0.06
     springs
    0.06
     ін
    0.06
    Act Density 0.012%

    No Known Activations