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

    Neuronpedia

    INDEX
    Explanations

    err

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Enforcement
    -0.07
     essentially
    -0.06
    澤
    -0.06
    κέ
    -0.06
    эй
    -0.06
    (n
    -0.06
     Welfare
    -0.06
     DEAD
    -0.05
     deeply
    -0.05
     collapse
    -0.05
    POSITIVE LOGITS
     Ran
    0.07
     Svens
    0.07
     Shir
    0.06
    皆
    0.06
     phận
    0.06
    istrar
    0.06
     Bengal
    0.06
     истории
    0.06
    ireccion
    0.06
    lacağ
    0.06
    Act Density 0.005%

    No Known Activations