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

    Neuronpedia

    INDEX
    Explanations

    :

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ndata
    -0.06
    'H
    -0.06
     cheap
    -0.06
     Saudis
    -0.06
     carbs
    -0.06
    Cache
    -0.06
     oci
    -0.06
    (style
    -0.06
     sağlar
    -0.06
    Achie
    -0.06
    POSITIVE LOGITS
     flock
    0.07
     faire
    0.06
     scal
    0.06
    ункци
    0.06
     sinon
    0.06
    andering
    0.06
     قابلیت
    0.06
    ::::/
    0.06
     alterations
    0.06
    针
    0.06
    Act Density 0.008%

    No Known Activations