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

    Neuronpedia

    INDEX
    Explanations

    gif

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _sc
    -0.07
    销
    -0.07
    ências
    -0.06
    ━━━━━━━━
    -0.06
    -wsj
    -0.06
     fmt
    -0.06
     tes
    -0.06
    dek
    -0.06
    __)
    -0.06
     усп
    -0.06
    POSITIVE LOGITS
     Agency
    0.07
    alfa
    0.07
    gif
    0.07
    _MULTI
    0.07
     gif
    0.07
     fighters
    0.07
     BMP
    0.06
     chiến
    0.06
    At
    0.06
    -cat
    0.06
    Act Density 0.001%

    No Known Activations