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

    Neuronpedia

    INDEX
    Explanations

    "in order to"

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     nối
    -0.07
    识别
    -0.07
    强力
    -0.07
    .Shapes
    -0.07
    .tele
    -0.07
     wirk
    -0.07
    孚
    -0.07
    难受
    -0.06
    イメ
    -0.06
    //------------------------------------------------------------------------------↵↵
    -0.06
    POSITIVE LOGITS
     Function
    0.07
     di
    0.07
    exchange
    0.07
    .CO
    0.07
    active
    0.07
    ской
    0.07
    ài
    0.07
    ез
    0.07
    acci
    0.07
    -cons
    0.06
    Act Density 0.075%

    No Known Activations