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

    Neuronpedia

    INDEX
    Explanations

    in

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    䨰
    -0.07
    率达到
    -0.06
    不存在
    -0.06
    אמן
    -0.06
     Rodgers
    -0.06
    ぽ
    -0.06
     funk
    -0.06
    不具备
    -0.06
     BTN
    -0.06
    身价
    -0.06
    POSITIVE LOGITS
    #----------------------------------------------------------------------------
    0.07
    αι
    0.07
    DRAM
    0.07
     Brow
    0.07
    Increases
    0.07
    oram
    0.07
     ord
    0.07
    oned
    0.07
    (iv
    0.07
    Plate
    0.07
    Act Density 0.000%

    No Known Activations