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

    Neuronpedia

    INDEX
    Explanations

    installation wizard

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ς
    0.72
    د
    0.71
    ม
    0.66
    ੦
    0.61
     be
    0.59
     cadeaux
    0.59
    րա
    0.58
     reintroduced
    0.58
    marès
    0.57
    ز
    0.57
    POSITIVE LOGITS
    coupling
    0.55
    ্নান
    0.55
     Hardin
    0.55
     Stepan
    0.54
    angle
    0.53
    fall
    0.52
     Clinton
    0.52
    emission
    0.51
     Smit
    0.51
    oil
    0.50
    Act Density 0.001%

    No Known Activations