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

    Neuronpedia

    INDEX
    Explanations

    warm-up exercises

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     тепер
    -0.07
     اليمن
    -0.07
     DEL
    -0.07
    219
    -0.07
     أخرى
    -0.07
    ини
    -0.06
    可以
    -0.06
     glac
    -0.06
     �
    -0.06
    Asia
    -0.06
    POSITIVE LOGITS
     kênh
    0.07
     vom
    0.07
    งก
    0.07
     idiots
    0.07
     daň
    0.06
     printf
    0.06
    .SetBool
    0.06
    structions
    0.06
    .putText
    0.06
     Paramount
    0.06
    Act Density 0.025%

    No Known Activations