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

    Neuronpedia

    INDEX
    Explanations

    /

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     zde
    -0.06
    台灣
    -0.06
    edx
    -0.06
    ्ल
    -0.06
    :',↵
    -0.06
     Stats
    -0.06
     landmark
    -0.06
    ニメ
    -0.06
     mav
    -0.06
    “
    -0.06
    POSITIVE LOGITS
     продовж
    0.07
    etas
    0.07
     each
    0.07
     Discovery
    0.06
     disarm
    0.06
    .cid
    0.06
    .IOException
    0.06
     manually
    0.06
    .win
    0.06
    navigate
    0.06
    Act Density 0.003%

    No Known Activations