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

    Neuronpedia

    INDEX
    Explanations

    SQL structures and operations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     following
    0.45
    縷
    0.44
    excellent
    0.42
     sounded
    0.41
    illation
    0.40
    ⟋
    0.40
     تك
    0.38
     fold
    0.38
    ට්ට
    0.37
    agro
    0.37
    POSITIVE LOGITS
    über
    0.43
     decât
    0.37
    arena
    0.37
    ܂
    0.37
    òria
    0.36
    tsx
    0.36
     Hasbro
    0.36
    inh
    0.36
    Nä
    0.36
    à
    0.36
    Act Density 0.000%

    No Known Activations