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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ιλο
    -0.07
    -high
    -0.07
     χρήση
    -0.07
     Eine
    -0.06
     arrangements
    -0.06
    ular
    -0.06
    머니
    -0.06
    Possible
    -0.06
    Yang
    -0.06
     noodles
    -0.06
    POSITIVE LOGITS
    osl
    0.07
    (","
    0.07
     strategist
    0.07
     Fountain
    0.07
     Copenhagen
    0.06
     của
    0.06
     impoverished
    0.06
    intelligence
    0.06
     FTC
    0.06
    (pub
    0.06
    Act Density 0.003%

    No Known Activations