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

    Neuronpedia

    INDEX
    Explanations

    unique identifier

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     atteggi
    0.81
     sailboats
    0.75
     pergunt
    0.70
     actitudes
    0.70
     야
    0.69
    豚
    0.69
     overthrow
    0.69
     shirtless
    0.69
     Muscles
    0.69
     स्तन
    0.68
    POSITIVE LOGITS
     UUID
    2.12
     unique
    2.09
    uuid
    2.09
    UUID
    2.05
     uuid
    2.02
     Unique
    1.98
    unique
    1.97
    Unique
    1.96
     uniqueness
    1.92
     uniquely
    1.82
    Act Density 0.975%

    No Known Activations