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

    Neuronpedia

    INDEX
    Explanations

    and

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     remain
    -0.07
    PUTE
    -0.06
     appellant
    -0.06
    skirts
    -0.06
    (repo
    -0.06
    :"",
    -0.06
     libr
    -0.06
    	Type
    -0.06
    _BEGIN
    -0.06
    Sat
    -0.06
    POSITIVE LOGITS
     İt
    0.07
    手
    0.07
     holland
    0.06
     Newly
    0.06
    .annotate
    0.06
    栏
    0.06
    解
    0.06
    iedy
    0.06
    .poly
    0.06
    uspended
    0.06
    Act Density 0.000%

    No Known Activations