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

    Neuronpedia

    INDEX
    Explanations

    Poland locations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    riteria
    -0.07
    easy
    -0.07
    ashtra
    -0.06
     former
    -0.06
    Volume
    -0.06
    ト
    -0.06
     عنه
    -0.06
    _ls
    -0.06
    _fecha
    -0.06
    .hp
    -0.06
    POSITIVE LOGITS
    (IM
    0.07
     Mind
    0.07
     υπ
    0.06
    邦
    0.06
     Blue
    0.06
     Din
    0.06
    iced
    0.06
    再
    0.06
    buff
    0.06
     και
    0.06
    Act Density 0.005%

    No Known Activations