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

    Neuronpedia

    INDEX
    Explanations

    situation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    strip
    -0.07
     reaches
    -0.07
    尚
    -0.07
    要是
    -0.07
     accidental
    -0.07
    都不知道
    -0.07
     notification
    -0.07
    },
↵
↵
    -0.07
    .Small
    -0.07
     ),↵↵
    -0.07
    POSITIVE LOGITS
    _pkt
    0.07
    民政
    0.07
    keleton
    0.07
     החו
    0.07
     deltaX
    0.07
     yür
    0.07
    �자
    0.07
    ictim
    0.07
     mga
    0.06
     svn
    0.06
    Act Density 0.079%

    No Known Activations