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

    Neuronpedia

    INDEX
    Explanations

    certificates and awards

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    RR
    -0.07
    EQ
    -0.07
     ballet
    -0.07
    JI
    -0.07
    넘
    -0.07
    比如
    -0.07
    .address
    -0.07
     BCE
    -0.06
     Nhưng
    -0.06
     Ket
    -0.06
    POSITIVE LOGITS
     Cecil
    0.06
     poor
    0.06
    ileges
    0.06
    UPDATE
    0.06
    houses
    0.06
     roofs
    0.06
     compassion
    0.06
    𬬿
    0.06
     Modular
    0.06
     offices
    0.06
    Act Density 0.017%

    No Known Activations