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

    Neuronpedia

    INDEX
    Explanations

    injunction

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    vious
    -0.07
     후
    -0.07
     ayant
    -0.07
    醢
    -0.07
    雄
    -0.07
     "");↵
    -0.07
     Alive
    -0.06
     bald
    -0.06
     gạo
    -0.06
     His
    -0.06
    POSITIVE LOGITS
    ibre
    0.08
    Indian
    0.07
    	record
    0.07
    倡议
    0.07
    _ops
    0.06
     qualifier
    0.06
    工作的
    0.06
     nghiệp
    0.06
    狀態
    0.06
     clashes
    0.06
    Act Density 0.002%

    No Known Activations