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

    Neuronpedia

    INDEX
    Explanations

    mechanisms processes events

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     litre
    -0.07
     //----------------
    -0.07
     gauge
    -0.07
    \Config
    -0.07
    !),
    -0.07
     ξ
    -0.06
    sweet
    -0.06
     itch
    -0.06
     strav
    -0.06
     verm
    -0.06
    POSITIVE LOGITS
    otine
    0.08
    تری
    0.06
    -producing
    0.06
     relational
    0.06
     focuses
    0.06
    ตำบล
    0.06
    container
    0.05
     CAS
    0.05
     Gul
    0.05
     portrays
    0.05
    Act Density 0.062%

    No Known Activations