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

    Neuronpedia

    INDEX
    Explanations

    working

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Fan
    -0.07
    .me
    -0.07
    _lead
    -0.07
     dissolved
    -0.06
    Offer
    -0.06
    .box
    -0.06
    德
    -0.06
     opposed
    -0.06
    Risk
    -0.06
    Leave
    -0.06
    POSITIVE LOGITS
     working
    0.08
    сі
    0.07
     minim
    0.07
     convinc
    0.07
     strongly
    0.06
    ibt
    0.06
    @register
    0.06
     getC
    0.06
     çalışma
    0.06
    ач
    0.06
    Act Density 0.020%

    No Known Activations