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

    Neuronpedia

    INDEX
    Explanations

    code/data

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ']."
    -0.07
    bstract
    -0.06
     }}↵↵
    -0.06
    cname
    -0.06
     Aws
    -0.06
     pregn
    -0.06
    =="
    -0.06
     corresponding
    -0.06
    .strict
    -0.06
    .getIn
    -0.05
    POSITIVE LOGITS
    _DESCRIPTOR
    0.07
    /head
    0.07
     Lifestyle
    0.07
    荣
    0.07
    ALA
    0.06
    违
    0.06
     miscar
    0.06
    ala
    0.06
    Bridge
    0.06
     Discover
    0.06
    Act Density 0.000%

    No Known Activations