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

    Neuronpedia

    INDEX
    Explanations

    getting

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    State
    -0.07
    COND
    -0.07
    מרכז
    -0.07
    価
    -0.07
     שקל
    -0.07
    啶
    -0.06
    _TEM
    -0.06
    注意力
    -0.06
    ꪜ
    -0.06
    .Cmd
    -0.06
    POSITIVE LOGITS
    catch
    0.07
     bottleneck
    0.07
    ickness
    0.07
     replica
    0.07
    严重影响
    0.07
    б
    0.07
     Usuarios
    0.07
     stabbed
    0.07
    宝石
    0.07
     pervasive
    0.06
    Act Density 0.045%

    No Known Activations