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

    Neuronpedia

    INDEX
    Explanations

    spoken word

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    овано
    -0.07
    (exports
    -0.07
    arning
    -0.07
    customers
    -0.06
    (Blueprint
    -0.06
    .language
    -0.06
    ience
    -0.06
    .formData
    -0.06
     Surveillance
    -0.06
     authenticated
    -0.06
    POSITIVE LOGITS
    ILES
    0.07
    漂
    0.07
     Hemisphere
    0.07
    .ItemStack
    0.07
     unl
    0.06
    nbr
    0.06
    ahan
    0.06
     밀
    0.06
    �
    0.06
    推薦
    0.06
    Act Density 0.016%

    No Known Activations