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

    Neuronpedia

    INDEX
    Explanations

    technical texts

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    🦶
    -0.06
    🚜
    -0.06
    orman
    -0.06
    Fixture
    -0.06
    urahan
    -0.06
     Lorem
    -0.06
    Hp
    -0.06
    一副
    -0.06
    ﱔ
    -0.06
    
    -0.06
    POSITIVE LOGITS
    repr
    0.08
     VAL
    0.08
     PR
    0.07
    osomal
    0.07
    北方
    0.07
    ТА
    0.07
     Aval
    0.06
     moved
    0.06
     Quân
    0.06
     всех
    0.06
    Act Density 0.349%

    No Known Activations