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

    Neuronpedia

    INDEX
    Explanations

    that

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .multipart
    -0.08
    sj
    -0.06
     vim
    -0.06
     때문에
    -0.06
    ToAdd
    -0.06
     removeFrom
    -0.06
     wins
    -0.06
     announcements
    -0.06
     Alamofire
    -0.06
    /run
    -0.06
    POSITIVE LOGITS
     who
    0.10
     which
    0.08
     Who
    0.08
    who
    0.08
    Who
    0.07
    (which
    0.07
     WHICH
    0.07
     wounds
    0.06
    вол
    0.06
     efect
    0.06
    Act Density 0.023%

    No Known Activations