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

    Neuronpedia

    INDEX
    Explanations

    file path manipulation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Heathrow
    0.49
     India
    0.44
     Ireland
    0.42
    ssh
    0.41
     Australia
    0.40
     Mitchell
    0.40
     Genesis
    0.40
     Africa
    0.39
     Keating
    0.39
     reinstated
    0.39
    POSITIVE LOGITS
    SELF
    0.45
    zelf
    0.43
    Sibling
    0.42
    카
    0.41
    ፉ
    0.41
    kwargs
    0.41
    Concluding
    0.41
    ൽ
    0.41
    ྭ
    0.40
    self
    0.39
    Act Density 0.049%

    No Known Activations