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

    Neuronpedia

    INDEX
    Explanations

    year

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     dyst
    -0.07
     वक
    -0.06
     άν
    -0.06
    .newLine
    -0.06
    ###↵↵
    -0.06
     groundwork
    -0.06
     вариан
    -0.06
    _TH
    -0.06
     admit
    -0.06
     GPUs
    -0.06
    POSITIVE LOGITS
    ematics
    0.08
    _resource
    0.07
    licer
    0.07
    ainers
    0.07
    izzly
    0.06
    eners
    0.06
     confused
    0.06
    Rib
    0.06
    722
    0.06
     fired
    0.06
    Act Density 0.000%

    No Known Activations