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

    Neuronpedia

    INDEX
    Explanations

    length units

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Reached
    -0.07
    nia
    -0.07
    뷰
    -0.06
    tl
    -0.06
    bee
    -0.06
    _Comm
    -0.06
    ffff
    -0.06
    也
    -0.06
    희
    -0.06
    کنان
    -0.06
    POSITIVE LOGITS
     EG
    0.06
     GLUT
    0.06
     gcc
    0.06
    ��
    0.06
     рук
    0.06
    руют
    0.06
    setTimeout
    0.06
     wah
    0.06
     сот
    0.06
     честь
    0.06
    Act Density 0.026%

    No Known Activations