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

    Neuronpedia

    INDEX
    Explanations

    math symbols

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    InSeconds
    -0.06
     عفش
    -0.06
    annya
    -0.06
     domác
    -0.06
     Jessie
    -0.06
     mirrors
    -0.06
     pagar
    -0.06
    ког
    -0.06
     peng
    -0.06
     어려
    -0.06
    POSITIVE LOGITS
    ‪
    0.07
    .asset
    0.06
     Mathematics
    0.06
    سة
    0.06
    -too
    0.06
    ु�
    0.06
    .Job
    0.06
    %%
    0.06
    boundary
    0.06
     rootNode
    0.06
    Act Density 0.006%

    No Known Activations