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

    Neuronpedia

    INDEX
    Explanations

    authors

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Tổ
    -0.07
    /service
    -0.07
    cac
    -0.07
    TestingModule
    -0.06
    /git
    -0.06
    咝
    -0.06
    ህ
    -0.06
    둠
    -0.06
    ˌ
    -0.06
     İz
    -0.06
    POSITIVE LOGITS
    сид
    0.07
    _dead
    0.07
     adj
    0.07
    decision
    0.07
    卫浴
    0.07
    хот
    0.07
    elle
    0.07
     pada
    0.06
    _priv
    0.06
    converter
    0.06
    Act Density 0.000%

    No Known Activations