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

    Neuronpedia

    INDEX
    Explanations

    plum

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .gallery
    -0.07
     Auf
    -0.07
     Download
    -0.06
    -cond
    -0.06
     carrots
    -0.06
     aime
    -0.06
     từng
    -0.06
     cater
    -0.06
    .tar
    -0.06
    aisy
    -0.06
    POSITIVE LOGITS
     Logistics
    0.08
    前夕
    0.07
    stopped
    0.07
     stiffness
    0.07
    /styles
    0.07
    AntiForgeryToken
    0.07
    rig
    0.07
    Debug
    0.07
    multip
    0.07
     knights
    0.07
    Act Density 1.272%

    No Known Activations