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

    Neuronpedia

    INDEX
    Explanations

    "ities"

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Coke
    -0.07
     hockey
    -0.06
     Woj
    -0.06
     throwError
    -0.06
    τηγορ
    -0.06
     exh
    -0.06
     Service
    -0.06
     reimbursement
    -0.06
     buffet
    -0.06
     rahatsız
    -0.06
    POSITIVE LOGITS
     Start
    0.07
    ansom
    0.06
    ــــ
    0.06
    _transform
    0.06
    ucha
    0.06
    品牌
    0.06
     женщина
    0.06
     кот
    0.06
    ivot
    0.06
     ellipse
    0.06
    Act Density 0.010%

    No Known Activations