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

    Neuronpedia

    INDEX
    Explanations

    foreign words

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    park
    -0.07
     nonlinear
    -0.06
     operation
    -0.06
     pct
    -0.06
    文化
    -0.06
    (connection
    -0.06
    .change
    -0.06
    .partial
    -0.06
     wid
    -0.06
     cake
    -0.06
    POSITIVE LOGITS
    (inst
    0.08
     osobní
    0.07
    	glog
    0.07
     Böl
    0.07
     lắng
    0.06
    ůst
    0.06
    skyt
    0.06
    TextStyle
    0.06
    )"↵
    0.06
    _pkt
    0.06
    Act Density 0.016%

    No Known Activations