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

    Neuronpedia

    INDEX
    Explanations

    then

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    /'.$
    -0.07
     招
    -0.07
     الدين
    -0.07
     Зак
    -0.07
    항
    -0.06
    焼
    -0.06
     SSC
    -0.06
    овар
    -0.06
     downwards
    -0.06
     Bowling
    -0.06
    POSITIVE LOGITS
    ोत
    0.06
     most
    0.06
     fairly
    0.06
    Authorization
    0.06
    activ
    0.06
    ‌گذ
    0.06
     kind
    0.06
     Work
    0.06
    atonin
    0.06
    Trying
    0.06
    Act Density 0.000%

    No Known Activations