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

    Neuronpedia

    INDEX
    Explanations

    medical treatment plans

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    كيل
    -0.07
    чук
    -0.07
    ytut
    -0.07
     cooperation
    -0.07
     cohort
    -0.06
    ;,
    -0.06
     último
    -0.06
    айте
    -0.06
     peut
    -0.06
     cinemas
    -0.06
    POSITIVE LOGITS
    dream
    0.06
     �
    0.06
     varlık
    0.06
     bf
    0.06
     Hollow
    0.06
    viron
    0.06
    عدد
    0.06
     UserControl
    0.06
    *))
    0.06
     pojist
    0.06
    Act Density 0.064%

    No Known Activations