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

    Neuronpedia

    INDEX
    Explanations

    but

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Dao
    -0.07
     왔
    -0.07
    ้าห
    -0.07
    ляють
    -0.07
    GetY
    -0.07
    .bank
    -0.07
     strt
    -0.07
     거야
    -0.06
     ebx
    -0.06
     

↵
    -0.06
    POSITIVE LOGITS
    _possible
    0.06
     بیم
    0.06
    ically
    0.06
    typed
    0.06
     efficiently
    0.06
     fragmented
    0.06
     deep
    0.06
     {
↵
    0.05
     completion
    0.05
    .Tools
    0.05
    Act Density 0.006%

    No Known Activations