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

    Neuronpedia

    INDEX
    Explanations

    almond

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    	service
    -0.07
     throwable
    -0.07
    用车
    -0.07
    .msg
    -0.07
    .mvp
    -0.07
    .Business
    -0.07
    อง
    -0.07
     '@
    -0.07
    _gpio
    -0.07
     ?><
    -0.07
    POSITIVE LOGITS
     terminals
    0.08
    子弹
    0.07
    мир
    0.07
    חוז
    0.07
     билет
    0.07
    厲
    0.07
    是指
    0.06
     clearance
    0.06
     cutoff
    0.06
    MAS
    0.06
    Act Density 0.003%

    No Known Activations