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

    Neuronpedia

    INDEX
    Explanations

    of

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Supplements
    -0.07
    DIRECT
    -0.06
     victory
    -0.06
    lv
    -0.06
     DAY
    -0.06
     decency
    -0.06
    ΥΝ
    -0.06
    ¾
    -0.06
     depict
    -0.06
    YOUR
    -0.06
    POSITIVE LOGITS
     از
    0.07
    これ
    0.07
    .getResource
    0.07
    ्प
    0.06
     errone
    0.06
    rens
    0.06
     směrem
    0.06
    (sig
    0.06
    ്�
    0.06
     objectId
    0.06
    Act Density 0.014%

    No Known Activations