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

    Neuronpedia

    INDEX
    Explanations

    politics

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    оза
    -0.07
    (currentUser
    -0.06
    .hidden
    -0.06
    ós
    -0.06
    --)
    -0.06
     ном
    -0.06
     predictable
    -0.06
     ==>
    -0.06
    095
    -0.06
    andel
    -0.06
    POSITIVE LOGITS
    Build
    0.07
    Rick
    0.06
    لل
    0.06
     misunderstand
    0.06
     Suzanne
    0.06
    ]!='
    0.06
     QAction
    0.06
     gettext
    0.06
    ственной
    0.06
     dashed
    0.06
    Act Density 0.577%

    No Known Activations