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

    Neuronpedia

    INDEX
    Explanations

    premises

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .ol
    -0.07
     statusBar
    -0.07
    羊
    -0.06
     Gly
    -0.06
     activity
    -0.06
     coats
    -0.06
    GLenum
    -0.06
    ItemCount
    -0.06
    酒
    -0.06
    学会
    -0.06
    POSITIVE LOGITS
     premises
    0.12
    ram
    0.09
     premise
    0.08
    μα
    0.08
    fred
    0.08
    μπ
    0.08
    Prem
    0.08
    ssa
    0.07
     remot
    0.07
    RAM
    0.07
    Act Density 0.005%

    No Known Activations