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

    Neuronpedia

    INDEX
    Explanations

    family

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     infer
    -0.07
    SEL
    -0.07
    ]+=
    -0.07
    odef
    -0.06
    伤
    -0.06
    见证了
    -0.06
    thag
    -0.06
    茅
    -0.06
     neuro
    -0.06
    dB
    -0.06
    POSITIVE LOGITS
     flown
    0.07
     sola
    0.07
     
↵
    0.07
     Slow
    0.07
     functioning
    0.07
     IOS
    0.07
    Как
    0.07
     sitcom
    0.07
     acordo
    0.07
    采取
    0.07
    Act Density 0.000%

    No Known Activations