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

    Neuronpedia

    INDEX
    Explanations

    couple of

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    fully
    -0.11
    uite
    -0.10
    rame
    -0.10
    robe
    -0.10
    attles
    -0.10
    íģ¼
    -0.10
    ouse
    -0.10
    rello
    -0.09
    rait
    -0.09
    ily
    -0.09
    POSITIVE LOGITS
    ts
    0.17
    hood
    0.16
    /single
    0.13
    aged
    0.12
    think
    0.11
    /group
    0.11
    estro
    0.11
     hundred
    0.11
    ault
    0.10
    led
    0.10
    Act Density 0.024%

    No Known Activations