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

    Neuronpedia

    INDEX
    Explanations

    up

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     بواسطة
    -0.07
    lero
    -0.07
     infect
    -0.07
     entered
    -0.07
     tall
    -0.06
     Orchestra
    -0.06
     officer
    -0.06
    	vo
    -0.06
    _terminal
    -0.06
    erg
    -0.06
    POSITIVE LOGITS
    Up
    0.07
    .mesh
    0.07
    up
    0.07
     rebuild
    0.06
     elő
    0.06
    sup
    0.06
     openness
    0.06
     вспом
    0.06
    acing
    0.06
     �
    0.06
    Act Density 0.037%

    No Known Activations