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

    Neuronpedia

    INDEX
    Explanations

    uncomment

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    oze
    -0.07
     planets
    -0.06
    §ظ
    -0.06
     mimic
    -0.06
     attempting
    -0.06
     Whether
    -0.06
     loss
    -0.06
    뉴
    -0.06
    hello
    -0.06
     perform
    -0.06
    POSITIVE LOGITS
    .inter
    0.08
    Interceptor
    0.07
     фев
    0.07
    kuk
    0.07
     要
    0.07
     insanlar
    0.07
     hasNext
    0.07
    __((
    0.07
     المست
    0.07
     ASN
    0.06
    Act Density 0.001%

    No Known Activations