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

    Neuronpedia

    INDEX
    Explanations

    pills or tablets

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    rx
    -0.08
     ASSIGN
    -0.08
    [${
    -0.08
    ('@
    -0.08
    Links
    -0.07
    
    -0.07
    -_
    -0.07
    -pe
    -0.07
    Mine
    -0.07
    -No
    -0.07
    POSITIVE LOGITS
     tablets
    0.07
    뱋
    0.07
    하겠다
    0.07
    ません
    0.07
    discount
    0.07
    ิด
    0.07
    foobar
    0.07
    떴
    0.07
     провер
    0.07
    retched
    0.06
    Act Density 0.005%

    No Known Activations