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

    Neuronpedia

    INDEX
    Explanations

    branding

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    -taking
    -0.07
    лина
    -0.06
     flower
    -0.06
     pulver
    -0.06
     mutually
    -0.06
     escape
    -0.06
     fracture
    -0.06
     parallel
    -0.06
     participate
    -0.06
    (boost
    -0.06
    POSITIVE LOGITS
     branding
    0.12
     branded
    0.10
     Rosie
    0.07
     Prague
    0.07
    _FLAGS
    0.07
    бин
    0.07
     transgender
    0.06
    _sc
    0.06
    _RCC
    0.06
     BAR
    0.06
    Act Density 0.003%

    No Known Activations