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

    Neuronpedia

    INDEX
    Explanations

    mental

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    िश
    -0.07
     province
    -0.07
     geen
    -0.07
     legitimacy
    -0.06
    	div
    -0.06
     communal
    -0.06
    евые
    -0.06
     Queensland
    -0.06
    ])-
    -0.06
     ecommerce
    -0.06
    POSITIVE LOGITS
     bodily
    0.07
    鼻
    0.07
    /em
    0.07
    गल
    0.07
     감
    0.07
    digital
    0.06
     Gren
    0.06
    Autom
    0.06
    titre
    0.06
    stakes
    0.06
    Act Density 0.006%

    No Known Activations