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

    Neuronpedia

    INDEX
    Explanations

    deaths/mortality

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    이며
    -0.07
    .axis
    -0.06
     věcí
    -0.06
    /master
    -0.06
     starvation
    -0.06
    .factory
    -0.06
     Barth
    -0.06
    (cert
    -0.06
    (ax
    -0.06
     cứng
    -0.06
    POSITIVE LOGITS
     echoes
    0.07
    納
    0.07
    /entity
    0.07
    osaur
    0.06
     nationwide
    0.06
     †
    0.06
    ecer
    0.06
     queda
    0.06
    wf
    0.06
    ою
    0.06
    Act Density 0.010%

    No Known Activations