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

    Neuronpedia

    INDEX
    Explanations

    CMS

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    !\
    -0.07
     das
    -0.07
    父
    -0.07
    ath
    -0.07
     whom
    -0.07
    NJ
    -0.06
    大师
    -0.06
    ax
    -0.06
    冠军
    -0.06
    agne
    -0.06
    POSITIVE LOGITS
     UITapGestureRecognizer
    0.08
    ﳣ
    0.08
     swinger
    0.08
    keywords
    0.08
    [edge
    0.08
     infusion
    0.07
     музык
    0.07
    wallet
    0.07
     пользоват
    0.07
    Ability
    0.07
    Act Density 0.621%

    No Known Activations