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

    Neuronpedia

    INDEX
    Explanations

    product descriptions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .Vector
    -0.08
    真皮
    -0.07
     pg
    -0.07
     pov
    -0.07
    .every
    -0.07
    /sm
    -0.06
    _dictionary
    -0.06
     interpretation
    -0.06
    Vel
    -0.06
    inea
    -0.06
    POSITIVE LOGITS
    噇
    0.07
    uner
    0.07
    ]|
    0.07
    wire
    0.07
    ших
    0.07
    ยะ
    0.07
    Hola
    0.07
    عال
    0.06
    érieur
    0.06
    海
    0.06
    Act Density 0.153%

    No Known Activations