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

    Neuronpedia

    INDEX
    Explanations

    use

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     quadrant
    -0.08
    yd
    -0.06
     jud
    -0.06
     cafeteria
    -0.06
    _th
    -0.05
     whisk
    -0.05
     punches
    -0.05
     pat
    -0.05
     Territories
    -0.05
     intellig
    -0.05
    POSITIVE LOGITS
    oca
    0.07
     �
    0.07
     aucun
    0.07
     zost
    0.07
    _Interface
    0.06
    mage
    0.06
    productive
    0.06
    _SHARED
    0.06
     souvent
    0.06
    �n
    0.06
    Act Density 0.001%

    No Known Activations