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

    Neuronpedia

    INDEX
    Explanations

    patients

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Merry
    -0.07
     crash
    -0.07
     freezes
    -0.07
     święt
    -0.06
     Chris
    -0.06
    utch
    -0.06
     cw
    -0.06
     auch
    -0.06
    ih
    -0.06
    (the
    -0.06
    POSITIVE LOGITS
    EmailAddress
    0.08
    ResourceId
    0.07
    样板
    0.07
    EMPTY
    0.07
    をつけ
    0.07
     Unary
    0.07
    _MethodInfo
    0.07
    韬
    0.07
     ...(
    0.07
    myfile
    0.07
    Act Density 0.024%

    No Known Activations