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

    Neuronpedia

    INDEX
    Explanations

    close second

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Lake
    -0.07
     Fernando
    -0.07
     storefront
    -0.07
    Bruce
    -0.06
    ervers
    -0.06
     Kid
    -0.06
    nder
    -0.06
    (center
    -0.06
     creek
    -0.06
    Brown
    -0.06
    POSITIVE LOGITS
     redirection
    0.07
     gathering
    0.06
    .shortcuts
    0.06
     recalling
    0.06
    _RESOLUTION
    0.06
    serialization
    0.06
    _DEF
    0.06
    ptive
    0.06
    astically
    0.06
    安排
    0.06
    Act Density 0.058%

    No Known Activations