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

    Neuronpedia

    INDEX
    Explanations

    any

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     treeNode
    -0.07
    thresh
    -0.07
    Height
    -0.06
     UserManager
    -0.06
     functions
    -0.06
     medical
    -0.06
    upport
    -0.06
    modes
    -0.06
     компании
    -0.06
    .Trans
    -0.06
    POSITIVE LOGITS
     alma
    0.07
     Ả
    0.07
    LIC
    0.06
     Able
    0.06
    _LARGE
    0.06
     แหล
    0.06
     MLM
    0.06
    ardown
    0.06
    震
    0.06
    (access
    0.06
    Act Density 0.022%

    No Known Activations