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

    Neuronpedia

    INDEX
    Explanations

    given

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _EX
    -0.07
    corlib
    -0.07
    олос
    -0.06
    _DISTANCE
    -0.06
    umn
    -0.06
    covery
    -0.06
     chatt
    -0.06
    dyn
    -0.06
    .MaxValue
    -0.06
     aux
    -0.06
    POSITIVE LOGITS
    �
    0.07
    664
    0.07
    Sac
    0.07
    ,date
    0.07
    .oracle
    0.06
     Laundry
    0.06
     अलग
    0.06
     Assuming
    0.06
    TriState
    0.06
    最後
    0.06
    Act Density 0.007%

    No Known Activations