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

    Neuronpedia

    INDEX
    Explanations

    spotting

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    increase
    -0.06
     ignor
    -0.06
    ्तक
    -0.06
    (ans
    -0.06
    .required
    -0.06
    ecera
    -0.06
    --)↵
    -0.06
    ementia
    -0.06
    рования
    -0.06
     вода
    -0.06
    POSITIVE LOGITS
     Scout
    0.12
     scout
    0.12
     spotted
    0.11
     scouting
    0.09
     scouts
    0.09
     spotting
    0.09
    lint
    0.08
     Scouts
    0.08
    outing
    0.07
     Spy
    0.07
    Act Density 0.004%

    No Known Activations