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

    Neuronpedia

    INDEX
    Explanations

    dedicated

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ئ
    -0.06
    (Filter
    -0.06
     architectures
    -0.06
     Processes
    -0.06
    elts
    -0.06
    Mathf
    -0.06
    暴
    -0.06
     bào
    -0.06
    periments
    -0.06
     Armstrong
    -0.06
    POSITIVE LOGITS
     Pom
    0.07
     Libre
    0.07
     vit
    0.07
     Glen
    0.07
     taped
    0.07
     CSC
    0.06
     strom
    0.06
     voy
    0.06
     прод
    0.06
     deleted
    0.06
    Act Density 0.012%

    No Known Activations