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

    Neuronpedia

    INDEX
    Explanations

    Stating opinions and honesty

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     _.
    -0.07
     destroy
    -0.07
     yanlış
    -0.07
     yola
    -0.06
    Experts
    -0.06
    SURE
    -0.06
    ि�
    -0.06
    -plane
    -0.06
    indrical
    -0.06
    .functional
    -0.06
    POSITIVE LOGITS
     والإ
    0.07
     Rosenstein
    0.06
    EW
    0.06
     derive
    0.06
    slides
    0.06
    анной
    0.06
    "},{"
    0.06
    ……」↵↵
    0.06
    ’ya
    0.06
     dialogue
    0.06
    Act Density 0.063%

    No Known Activations