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

    Neuronpedia

    INDEX
    Explanations

    rate

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Erot
    -0.06
    样
    -0.06
    訓
    -0.06
    иплом
    -0.06
    emi
    -0.06
    얼
    -0.06
    hawk
    -0.06
     hình
    -0.06
     entertain
    -0.06
    -chevron
    -0.06
    POSITIVE LOGITS
     socialist
    0.06
     complains
    0.06
     prom
    0.06
     Cur
    0.06
    PC
    0.06
     composing
    0.06
    >f
    0.06
     teg
    0.06
    MH
    0.06
     MP
    0.06
    Act Density 0.001%

    No Known Activations