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

    Neuronpedia

    INDEX
    Explanations

    directly

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _TREE
    -0.07
     Mang
    -0.06
     �
    -0.06
     Moose
    -0.06
     середови
    -0.06
     افر
    -0.06
    实验
    -0.06
     бути
    -0.06
     Absolutely
    -0.06
     mans
    -0.06
    POSITIVE LOGITS
    直接
    0.09
     directly
    0.08
    elas
    0.07
    direct
    0.07
     Şubat
    0.06
     since
    0.06
     нич
    0.06
     après
    0.06
    aggio
    0.06
    в
    0.06
    Act Density 0.025%

    No Known Activations