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

    Neuronpedia

    INDEX
    Explanations

    Quotations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     MPU
    -0.07
    _GROUPS
    -0.07
    _MON
    -0.07
     Van
    -0.07
     שהם
    -0.07
    族
    -0.07
     miesią
    -0.07
     Squad
    -0.07
    Ptr
    -0.07
    -spec
    -0.07
    POSITIVE LOGITS
    �
    0.08
     palate
    0.08
    ilik
    0.07
    kowski
    0.07
    	Return
    0.07
     �
    0.07
    osition
    0.07
    叹
    0.07
    �示
    0.07
    cs
    0.07
    Act Density 0.057%

    No Known Activations