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
    čka
    -0.07
     Stevens
    -0.06
     지난
    -0.06
     nef
    -0.06
    比例
    -0.06
     palabras
    -0.06
     fox
    -0.06
     Nová
    -0.06
     cropped
    -0.06
     befind
    -0.06
    POSITIVE LOGITS
    )||
    0.08
    :NS
    0.08
     nightmare
    0.07
    _try
    0.07
    ||
    0.07
     &&
    0.07
    .Xr
    0.07
     �
    0.07
     Ens
    0.07
    longitude
    0.06
    Act Density 0.012%

    No Known Activations