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

    Neuronpedia

    INDEX
    Explanations

    are

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Sof
    -0.07
    -F
    -0.07
     NDP
    -0.06
    -law
    -0.06
     nep
    -0.06
     Kids
    -0.06
     €
    -0.06
    -y
    -0.06
    -H
    -0.06
     yards
    -0.05
    POSITIVE LOGITS
    ска
    0.07
    olulu
    0.07
     hardcoded
    0.07
     boto
    0.06
    τικο
    0.06
     Ấn
    0.06
    urd
    0.06
     Hyderabad
    0.06
     Fa
    0.06
    يلا
    0.06
    Act Density 0.169%

    No Known Activations