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

    Neuronpedia

    INDEX
    Explanations

    code snippets and forums

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    tape
    -0.07
    реб
    -0.07
     confl
    -0.07
    رة
    -0.07
    <l
    -0.07
     mary
    -0.07
    	rect
    -0.07
    pressed
    -0.06
    Barcode
    -0.06
     ])↵
    -0.06
    POSITIVE LOGITS
    _percent
    0.06
     bzw
    0.06
     dizzy
    0.06
    aliyet
    0.06
    ữ
    0.06
     oa
    0.06
    ỗng
    0.06
    oting
    0.06
    rıca
    0.06
     LTC
    0.06
    Act Density 0.106%

    No Known Activations