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

    Neuronpedia

    INDEX
    Explanations

    against

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     pag
    -0.07
    🐷
    -0.07
    ATTLE
    -0.07
    分离
    -0.07
     derived
    -0.06
     gefunden
    -0.06
    魈
    -0.06
     fd
    -0.06
     panels
    -0.06
    equal
    -0.06
    POSITIVE LOGITS
     LSU
    0.07
     Herbert
    0.07
     fours
    0.07
    ₲
    0.07
    -orange
    0.06
    롞
    0.06
     rawData
    0.06
    ency
    0.06
     terrific
    0.06
    什么原因
    0.06
    Act Density 0.623%

    No Known Activations