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

    Neuronpedia

    INDEX
    Explanations

    good

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     suit
    -0.06
     surve
    -0.06
     ↵            ↵
    -0.06
    lá
    -0.06
    _TOOL
    -0.06
    bounce
    -0.06
    .tiles
    -0.06
    ".↵↵↵↵
    -0.06
    utations
    -0.06
     Principle
    -0.06
    POSITIVE LOGITS
    express
    0.08
     inbound
    0.07
     slab
    0.06
    drm
    0.06
     Slots
    0.06
     enforcing
    0.06
     reperc
    0.06
    /net
    0.06
    \Container
    0.06
    .squeeze
    0.06
    Act Density 0.031%

    No Known Activations