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

    Neuronpedia

    INDEX
    Explanations

    elevated

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     कह
    -0.07
     öğretmen
    -0.07
    892
    -0.06
    üler
    -0.06
     Bik
    -0.06
    _triggered
    -0.06
    、や
    -0.06
    (sorted
    -0.06
    plaintext
    -0.06
     sims
    -0.06
    POSITIVE LOGITS
    }->
    0.07
    ≠
    0.07
    люча
    0.07
     Mass
    0.06
    ».↵
    0.06
    اكن
    0.06
    }<
    0.06
    })
    0.06
    seud
    0.06
     стро
    0.06
    Act Density 0.310%

    No Known Activations