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

    Neuronpedia

    INDEX
    Explanations

    Code snippets and URLs

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     buffs
    -0.08
     dik
    -0.07
    _STRUCT
    -0.07
    ↷
    -0.07
    _oid
    -0.07
     bd
    -0.07
    _SEQ
    -0.07
    _BOOL
    -0.07
     iterators
    -0.07
    ❀
    -0.07
    POSITIVE LOGITS
    better
    0.07
    licable
    0.07
    iện
    0.07
    煁
    0.06
    珍惜
    0.06
    ]])
    0.06
     Citizenship
    0.06
    ']),
    0.06
    见过
    0.06
    当晚
    0.06
    Act Density 0.075%

    No Known Activations