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

    Neuronpedia

    INDEX
    Explanations

    upper

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     corpses
    -0.07
    )'],↵
    -0.07
     })),↵
    -0.07
    ี่
    -0.07
    redirect
    -0.07
    uku
    -0.06
    '})↵
    -0.06
     NU
    -0.06
    -brand
    -0.06
    ])))↵
    -0.06
    POSITIVE LOGITS
    _pipe
    0.07
    ToLower
    0.07
     klass
    0.07
    =-=-
    0.07
    predicate
    0.07
    �
    0.06
     Filed
    0.06
    나는
    0.06
     carp
    0.06
     dictates
    0.06
    Act Density 0.012%

    No Known Activations