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

    Neuronpedia

    INDEX
    Explanations

    ge

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    一批
    -0.08
     đâu
    -0.07
     dl
    -0.07
    下午
    -0.07
    wand
    -0.06
    婼
    -0.06
    症
    -0.06
     PublicKey
    -0.06
    .nextDouble
    -0.06
    当你
    -0.06
    POSITIVE LOGITS
    Argument
    0.09
     poems
    0.08
    高昂
    0.07
    .MSG
    0.07
    吓得
    0.07
     fopen
    0.07
    何度も
    0.07
     proofs
    0.07
     poem
    0.07
    .Messages
    0.06
    Act Density 0.005%

    No Known Activations