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

    Neuronpedia

    INDEX
    Explanations

    scientific notation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    OTE
    -0.07
     Banco
    -0.07
    filtro
    -0.06
    fps
    -0.06
    اءات
    -0.06
    (team
    -0.06
     Klein
    -0.06
    (chunk
    -0.06
     tutorials
    -0.06
    .There
    -0.06
    POSITIVE LOGITS
     πραγμα
    0.07
    Appear
    0.06
     کامل
    0.06
     شده
    0.06
     був
    0.06
    .sulake
    0.06
     aes
    0.06
     عالم
    0.06
     milyon
    0.06
    Hook
    0.06
    Act Density 0.005%

    No Known Activations