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

    Neuronpedia

    INDEX
    Explanations

    academic source material

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     데
    -0.08
    _gray
    -0.08
     됩니다
    -0.07
     �
    -0.07
    _decl
    -0.07
     팔
    -0.07
    gray
    -0.07
     Aquí
    -0.07
    _cn
    -0.07
     �
    -0.07
    POSITIVE LOGITS
     famously
    0.10
    Applicant
    0.08
     bekannte
    0.08
     falsa
    0.08
     pertinente
    0.08
     bekende
    0.08
     dominante
    0.08
    Appointments
    0.08
     famosa
    0.08
     доставка
    0.08
    Act Density 0.032%

    No Known Activations