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

    Neuronpedia

    INDEX
    Explanations

    >

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ailed
    -0.07
     ymax
    -0.07
     isNew
    -0.06
     Mine
    -0.06
    олю
    -0.06
    "https
    -0.06
     Eis
    -0.06
     Nüfus
    -0.06
    _RUNTIME
    -0.06
    dry
    -0.06
    POSITIVE LOGITS
    committee
    0.07
    Anc
    0.06
     character
    0.06
    妹
    0.06
    433
    0.06
     forbidden
    0.06
    (argc
    0.06
     shades
    0.06
    IMIT
    0.06
    角色
    0.06
    Act Density 0.041%

    No Known Activations