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

    Neuronpedia

    INDEX
    Explanations

    gave

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ">

↵
    -0.08
    	TokenNameIdentifier
    -0.07
    İTESİ
    -0.07
    "For
    -0.06
     Mercury
    -0.06
     soukrom
    -0.06
     Exchange
    -0.06
    _records
    -0.06
    517
    -0.06
    igious
    -0.06
    POSITIVE LOGITS
     }}}
    0.07
    .Warning
    0.06
    仕事
    0.06
    向
    0.06
    ित
    0.06
    κτη
    0.06
     Invoke
    0.06
    υχ
    0.06
    }}}
    0.06
     tri
    0.06
    Act Density 0.796%

    No Known Activations