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

    Neuronpedia

    INDEX
    Explanations

    website code/identifiers

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Lang
    -0.09
     Clo
    -0.08
    _BOUND
    -0.08
    Times
    -0.08
     Lang
    -0.08
    岁
    -0.08
     दर्शन
    -0.08
    。我
    -0.08
    -times
    -0.08
    ЕД
    -0.07
    POSITIVE LOGITS
     riding
    0.08
     disappear
    0.08
     attend
    0.08
     })
↵
↵
    0.08
     mante
    0.08
    })
↵
↵
    0.08
     сотруд
    0.08
     collaborator
    0.08
    opolis
    0.07
     Rihanna
    0.07
    Act Density 0.000%

    No Known Activations