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

    Neuronpedia

    INDEX
    Explanations

    @

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _keyboard
    -0.07
     rop
    -0.07
     shortcomings
    -0.07
    ATH
    -0.07
     �
    -0.06
    �
    -0.06
    tractive
    -0.06
     dictates
    -0.06
    ;|
    -0.06
     reusable
    -0.06
    POSITIVE LOGITS
    alars
    0.06
     Balk
    0.06
    させ
    0.06
     Afghan
    0.06
    ська
    0.06
     taking
    0.06
     msm
    0.06
     назнач
    0.06
     Wilmington
    0.06
    沿
    0.06
    Act Density 0.038%

    No Known Activations