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
    OCK
    -0.08
    XX
    -0.07
     activate
    -0.07
    arks
    -0.07
    AVA
    -0.07
    avl
    -0.07
     "":↵
    -0.06
     fyz
    -0.06
     stomach
    -0.06
    nero
    -0.06
    POSITIVE LOGITS
     obtener
    0.07
     fwd
    0.07
     idi
    0.06
     ideological
    0.06
    uesday
    0.06
    ÷
    0.06
     sidew
    0.06
    (tasks
    0.06
    working
    0.06
     nicely
    0.06
    Act Density 0.001%

    No Known Activations