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

    Neuronpedia

    INDEX
    Explanations

    oration

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .Cancel
    -0.07
    .targets
    -0.07
     "%.
    -0.07
     models
    -0.07
    _gray
    -0.07
    /color
    -0.06
    iguiente
    -0.06
    elled
    -0.06
    .Qual
    -0.06
     baseURL
    -0.06
    POSITIVE LOGITS
    everyone
    0.07
     bara
    0.06
     AN
    0.06
     Happiness
    0.06
     Mou
    0.06
     Riy
    0.06
     Slam
    0.06
     Mp
    0.06
    jug
    0.06
     Kant
    0.06
    Act Density 0.242%

    No Known Activations