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

    Neuronpedia

    INDEX
    Explanations

    unseen/hidden

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    پر
    -0.06
    ín
    -0.06
     zbo
    -0.06
    Memcpy
    -0.06
    amento
    -0.06
     зер
    -0.05
    ISTA
    -0.05
    อนท
    -0.05
     　　　
    -0.05
    �
    -0.05
    POSITIVE LOGITS
     Gross
    0.08
    ौं
    0.07
     Alcohol
    0.07
     Marker
    0.07
    ��
    0.07
     pirate
    0.07
     válido
    0.07
     proudly
    0.06
    _Date
    0.06
     Careers
    0.06
    Act Density 0.096%

    No Known Activations