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

    Neuronpedia

    INDEX
    Explanations

    and

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    етод
    -0.07
    这一
    -0.07
     guru
    -0.07
     publishes
    -0.07
    querque
    -0.07
     anch
    -0.06
     UnityEditor
    -0.06
    ассив
    -0.06
    preset
    -0.06
    (artist
    -0.06
    POSITIVE LOGITS
     imb
    0.06
    μένος
    0.06
     stores
    0.06
     Provid
    0.06
    TON
    0.06
    .printf
    0.06
    ोम
    0.06
     homicides
    0.05
     workers
    0.05
     pours
    0.05
    Act Density 0.025%

    No Known Activations