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

    Neuronpedia

    INDEX
    Explanations

    able

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .,
    -0.06
    bucks
    -0.06
    wner
    -0.06
     Pry
    -0.06
     Dynasty
    -0.06
     neutron
    -0.06
     муз
    -0.06
     Kč
    -0.06
    ']]['
    -0.06
     Governments
    -0.06
    POSITIVE LOGITS
     occasions
    0.07
    acing
    0.07
     encouraging
    0.06
    其中
    0.06
    .converter
    0.06
     succeeding
    0.06
     teenagers
    0.06
    -mail
    0.06
    υνα
    0.06
    �
    0.06
    Act Density 0.000%

    No Known Activations