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

    Neuronpedia

    INDEX
    Explanations

    getting information

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    acement
    -0.07
     Worse
    -0.06
     qualifies
    -0.06
    Attached
    -0.06
     distracting
    -0.06
    aded
    -0.06
    /in
    -0.06
     Veterans
    -0.06
    最后一次
    -0.06
    stantiate
    -0.06
    POSITIVE LOGITS
     הזאת
    0.07
    onde
    0.07
    蜀
    0.07
    paper
    0.07
     włos
    0.07
     glossy
    0.06
    nex
    0.06
    ☤
    0.06
     vines
    0.06
    ouro
    0.06
    Act Density 0.824%

    No Known Activations