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

    Neuronpedia

    INDEX
    Explanations

    eligibility criteria

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Unload
    -0.07
    BCM
    -0.07
    Dto
    -0.07
    <n
    -0.06
    رد
    -0.06
    Tuple
    -0.06
    Sadly
    -0.06
     mặc
    -0.06
    "To
    -0.06
    \">↵
    -0.06
    POSITIVE LOGITS
     التح
    0.06
    periments
    0.06
     Void
    0.06
    graphics
    0.06
    _pal
    0.06
     DIS
    0.06
    (create
    0.06
     Bol
    0.06
    чики
    0.06
     tonnes
    0.06
    Act Density 0.199%

    No Known Activations