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

    Neuronpedia

    INDEX
    Explanations

    scientific hypotheses

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    quets
    -0.07
     �
    -0.06
    arias
    -0.06
     psychotic
    -0.06
     imap
    -0.06
    努
    -0.06
     snack
    -0.06
     pairwise
    -0.06
    peed
    -0.06
    987
    -0.06
    POSITIVE LOGITS
    :(
    0.07
    ">\
    0.06
    :///
    0.06
     "{\"
    0.06
    Condition
    0.06
     ***↵
    0.06
    [,
    0.06
     attributed
    0.06
    (':',
    0.06
    (robot
    0.06
    Act Density 0.177%

    No Known Activations