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

    Neuronpedia

    INDEX
    Explanations

    those

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    push
    -0.06
    overlay
    -0.06
    匹
    -0.06
    ]]=
    -0.06
     clockwise
    -0.06
    引き
    -0.06
     push
    -0.06
    Amb
    -0.06
    ограм
    -0.06
    <dynamic
    -0.06
    POSITIVE LOGITS
    Online
    0.06
     ratio
    0.06
     tutor
    0.06
     Conn
    0.06
     Ghost
    0.06
     schedule
    0.06
    рей
    0.06
     Tutor
    0.06
     xác
    0.06
    	Block
    0.06
    Act Density 0.040%

    No Known Activations