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

    Neuronpedia

    INDEX
    Explanations

    legal disclaimers and permissions

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     restrictive
    -0.08
    _FAST
    -0.07
    *(-
    -0.07
    chair
    -0.07
    (Dense
    -0.06
     promotes
    -0.06
    期间
    -0.06
    .vm
    -0.06
    ตำ
    -0.06
     dlouhodob
    -0.06
    POSITIVE LOGITS
     Mc
    0.07
     informatie
    0.07
     Mean
    0.06
    agos
    0.06
    visející
    0.06
    _xs
    0.06
    �
    0.06
     poids
    0.06
     panor
    0.06
     Redistributions
    0.06
    Act Density 0.058%

    No Known Activations