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

    Neuronpedia

    INDEX
    Explanations

    True

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    velte
    -0.07
     connector
    -0.06
    Material
    -0.06
     GMT
    -0.06
     userRepository
    -0.06
    mbH
    -0.06
     PARTICULAR
    -0.06
    veillance
    -0.06
     vẽ
    -0.06
    /model
    -0.06
    POSITIVE LOGITS
    цо
    0.08
    ��
    0.06
    ��
    0.06
    tu
    0.06
    ruary
    0.06
    |RF
    0.06
    sent
    0.06
    	audio
    0.06
     Sent
    0.06
     muzzle
    0.06
    Act Density 0.003%

    No Known Activations