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

    Neuronpedia

    INDEX
    Explanations

    ^

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     $('#'
    -0.07
     moving
    -0.07
     clumsy
    -0.07
    ۍ
    -0.07
    reopen
    -0.07
    两手
    -0.07
    _makeConstraints
    -0.07
    跐
    -0.07
     "{"
    -0.06
     onFocus
    -0.06
    POSITIVE LOGITS
    /******/
    0.07
    英國
    0.07
     synthes
    0.07
    Echo
    0.07
    ости
    0.07
     Here
    0.07
    旗下的
    0.07
    mort
    0.07
     Assassin
    0.07
    =-
    0.06
    Act Density 0.002%

    No Known Activations