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

    Neuronpedia

    INDEX
    Explanations

    .

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    oles
    -0.07
     Platinum
    -0.07
    orbit
    -0.07
    лена
    -0.06
    	lines
    -0.06
     sands
    -0.06
    ána
    -0.06
     ire
    -0.06
     tm
    -0.06
    ToSend
    -0.06
    POSITIVE LOGITS
    .NewReader
    0.07
    ,j
    0.07
    .Exists
    0.06
    阿
    0.06
    prisingly
    0.06
     همان
    0.06
     newState
    0.06
     строитель
    0.06
    (UnmanagedType
    0.06
    러스
    0.06
    Act Density 0.054%

    No Known Activations