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

    Neuronpedia

    INDEX
    Explanations

    .com

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .JPG
    -0.07
     św
    -0.07
    堼
    -0.07
     yük
    -0.07
    eroon
    -0.07
    中考
    -0.07
     readme
    -0.07
    从来没
    -0.06
    xmin
    -0.06
     קודם
    -0.06
    POSITIVE LOGITS
     findings
    0.07
     COMMAND
    0.07
     Bright
    0.07
     currency
    0.06
     terra
    0.06
     consequences
    0.06
    __":↵
    0.06
     directly
    0.06
    -ball
    0.06
     Richard
    0.06
    Act Density 0.003%

    No Known Activations