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

    Neuronpedia

    INDEX
    Explanations

    offspring

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    	show
    -0.07
    -grow
    -0.07
     tấn
    -0.06
     nguyện
    -0.06
    VIEW
    -0.06
    takes
    -0.06
     Fit
    -0.06
     glean
    -0.06
     topLevel
    -0.06
     forging
    -0.06
    POSITIVE LOGITS
    );;↵
    0.08
     리스트
    0.08
     coli
    0.07
    .strategy
    0.07
     rôle
    0.07
    之间
    0.07
    𝓪
    0.07
    这句话
    0.07
     przed
    0.07
     Gonzalez
    0.06
    Act Density 0.031%

    No Known Activations