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

    Neuronpedia

    INDEX
    Explanations

    test

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    =DB
    -0.07
    ็ต
    -0.06
     DEF
    -0.06
     peanuts
    -0.06
     DON
    -0.06
    มข
    -0.06
    \Command
    -0.06
     či
    -0.06
     ทาง
    -0.06
    alles
    -0.06
    POSITIVE LOGITS
    急
    0.07
     jednoho
    0.06
    โย
    0.06
     nie
    0.06
    -safe
    0.06
    (withDuration
    0.06
    imeo
    0.06
    Magic
    0.06
     surgeon
    0.06
    imd
    0.06
    Act Density 0.000%

    No Known Activations