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

    Neuronpedia

    INDEX
    Explanations

    -label

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Gameplay
    -0.07
    undy
    -0.07
    _com
    -0.07
    斗
    -0.07
    nte
    -0.07
    ជ
    -0.07
    izz
    -0.07
    找准
    -0.07
    พ
    -0.07
    中铁
    -0.07
    POSITIVE LOGITS
    .savetxt
    0.08
    ሌ
    0.07
     murderer
    0.07
     друз
    0.07
     Todos
    0.07
     Haven
    0.07
     exhaustion
    0.07
     حاج
    0.07
     cultiv
    0.07
     burgers
    0.07
    Act Density 0.000%

    No Known Activations