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

    Neuronpedia

    INDEX
    Explanations

    force

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     synth
    -0.07
     record
    -0.07
    kest
    -0.07
    كت
    -0.07
     Heather
    -0.07
    يخ
    -0.07
     ч
    -0.07
    純
    -0.07
    蘇
    -0.06
    ��
    -0.06
    POSITIVE LOGITS
     RTVF
    0.08
    Downloader
    0.07
    DOCKER
    0.07
    _trajectory
    0.07
    	swap
    0.07
    '))
↵
    0.07
    Downloads
    0.07
    外语
    0.06
     }}
    0.06
    accordion
    0.06
    Act Density 0.010%

    No Known Activations