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

    Neuronpedia

    INDEX
    Explanations

    programming file paths/links

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     offering
    -0.07
     forming
    -0.07
     Kid
    -0.07
    小店
    -0.07
    全国各地
    -0.07
    广播电视
    -0.06
     promotional
    -0.06
     metal
    -0.06
    .OutputStream
    -0.06
    𤫉
    -0.06
    POSITIVE LOGITS
    .Criteria
    0.07
    lb
    0.07
    Interestingly
    0.07
     ig
    0.07
    aphore
    0.06
    flu
    0.06
    gars
    0.06
     правила
    0.06
    ologna
    0.06
    �
    0.06
    Act Density 0.082%

    No Known Activations