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

    Neuronpedia

    INDEX
    Explanations

    about

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Trib
    -0.07
     oder
    -0.07
    _written
    -0.06
     beden
    -0.06
    _cycle
    -0.06
     raced
    -0.06
     borrowers
    -0.06
     Sır
    -0.06
     말
    -0.06
     мор
    -0.06
    POSITIVE LOGITS
    UpDown
    0.07
    	Expect
    0.07
    0.06
    �
    0.06
    律
    0.06
    РН
    0.06
    632
    0.06
    alborg
    0.06
    .EventType
    0.06
     ре
    0.06
    Act Density 0.019%

    No Known Activations