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

    Neuronpedia

    INDEX
    Explanations

    uction

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     अव
    -0.08
    运动
    -0.07
    联盟
    -0.07
     Mafia
    -0.06
     wrong
    -0.06
     Когда
    -0.06
    าจะ
    -0.06
     Hong
    -0.06
    95
    -0.06
     araya
    -0.06
    POSITIVE LOGITS
    дел
    0.07
     progressively
    0.07
     induction
    0.07
     Jess
    0.06
    _TOGGLE
    0.06
     ]
↵
    0.06
    /from
    0.06
     /:
    0.06
     UINT
    0.06
     postpon
    0.06
    Act Density 0.005%

    No Known Activations