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

    Neuronpedia

    INDEX
    Explanations

    slurs

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    -money
    -0.07
     hora
    -0.07
     د
    -0.07
    砂
    -0.07
    TRS
    -0.07
    301
    -0.07
    毛
    -0.07
     Instance
    -0.06
    éné
    -0.06
    OTE
    -0.06
    POSITIVE LOGITS
    Successfully
    0.08
     htonl
    0.06
    WindowSize
    0.06
     assertFalse
    0.06
    整个
    0.06
    hive
    0.06
    увалися
    0.06
    为空
    0.06
     Queries
    0.06
    Attr
    0.05
    Act Density 0.011%

    No Known Activations