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

    Neuronpedia

    INDEX
    Explanations

    "Imagine" contexts

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Weed
    -0.06
    @Component
    -0.06
     Salary
    -0.06
     đĩa
    -0.06
    dummy
    -0.06
     getter
    -0.06
    Henry
    -0.06
    -most
    -0.06
    Directions
    -0.06
    inning
    -0.05
    POSITIVE LOGITS
     lying
    0.07
    ",@"
    0.07
    activo
    0.07
    oại
    0.07
     Goodman
    0.06
     enqueue
    0.06
     Scout
    0.06
    /login
    0.06
     corporate
    0.06
    ahtar
    0.06
    Act Density 0.033%

    No Known Activations