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

    Neuronpedia

    INDEX
    Explanations

    c

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     싱
    -0.06
    考试
    -0.06
    bcm
    -0.06
    ony
    -0.06
     disrupt
    -0.06
    ties
    -0.06
     существует
    -0.06
    .Vert
    -0.06
    osyal
    -0.06
     ℝ
    -0.06
    POSITIVE LOGITS
     enticing
    0.07
    antha
    0.07
    Fd
    0.07
     nhẹ
    0.07
     Ấ
    0.06
     spender
    0.06
    ่อน
    0.06
    undler
    0.06
    六
    0.06
     tuyệt
    0.06
    Act Density 0.036%

    No Known Activations