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

    Neuronpedia

    INDEX
    Explanations

    Featured

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     checklist
    -0.07
    좀
    -0.07
     villages
    -0.07
    Report
    -0.07
    closing
    -0.07
     poorest
    -0.07
     inbox
    -0.06
    (S
    -0.06
     lidí
    -0.06
    によ
    -0.06
    POSITIVE LOGITS
    Featured
    0.08
     Thought
    0.07
    Stub
    0.07
     уча
    0.07
    Feature
    0.07
     assort
    0.06
     Feature
    0.06
     grub
    0.06
     getEmail
    0.06
    inium
    0.06
    Act Density 0.001%

    No Known Activations