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

    Neuronpedia

    INDEX
    Explanations

    which

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ่าว
    -0.07
     repeat
    -0.07
     nord
    -0.07
     nug
    -0.07
     ze
    -0.07
     ста
    -0.07
     regiment
    -0.06
    .mixer
    -0.06
     of
    -0.06
     пог
    -0.06
    POSITIVE LOGITS
    weigh
    0.07
    ereco
    0.07
     descricao
    0.07
     филь
    0.07
     jehož
    0.07
    //=
    0.06
    Thank
    0.06
    ��
    0.06
     },↵
    0.06
    liable
    0.06
    Act Density 0.011%

    No Known Activations