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

    Neuronpedia

    INDEX
    Explanations

    informational texts

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     otro
    -0.07
    ا�
    -0.07
     barg
    -0.07
     yanlış
    -0.07
     charging
    -0.07
     pasar
    -0.07
     policies
    -0.06
     judicial
    -0.06
    _None
    -0.06
    -positive
    -0.06
    POSITIVE LOGITS
     REPL
    0.07
    (This
    0.06
    cookie
    0.06
    iệ
    0.06
    _Ref
    0.06
    ีส
    0.06
     cep
    0.06
    bew
    0.06
    ustin
    0.06
    ]]);↵
    0.06
    Act Density 0.080%

    No Known Activations