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

    Neuronpedia

    INDEX
    Explanations

    phone numbers

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    год
    -0.07
    िथ
    -0.07
    vio
    -0.07
     riding
    -0.06
    ZD
    -0.06
    Faces
    -0.06
     至
    -0.06
    Includes
    -0.06
    ENTIC
    -0.06
     Bethlehem
    -0.06
    POSITIVE LOGITS
     вив
    0.06
    latent
    0.06
    (worker
    0.06
    σιμοποι
    0.06
    真正
    0.06
     Bachelor
    0.05
    stå
    0.05
    aşa
    0.05
     poner
    0.05
    ekkür
    0.05
    Act Density 0.025%

    No Known Activations