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

    Neuronpedia

    INDEX
    Explanations

    of

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     invested
    -0.07
    -minded
    -0.06
    ậy
    -0.06
    ера
    -0.06
    ájem
    -0.06
    annel
    -0.06
    ülü
    -0.06
    \S
    -0.06
    OUND
    -0.06
    (Character
    -0.06
    POSITIVE LOGITS
     PIXI
    0.07
    -best
    0.06
    洲
    0.06
     خود
    0.06
    .ibatis
    0.06
     Petsc
    0.06
    handle
    0.06
     مختلف
    0.06
     ITV
    0.06
    '));
    0.06
    Act Density 0.029%

    No Known Activations