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

    Neuronpedia

    INDEX
    Explanations

    biological organisms, cells, and species

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    aneous
    0.75
    ando
    0.71
    ien
    0.66
    ian
    0.64
    xiety
    0.64
     E
    0.64
    enciar
    0.64
     conducting
    0.63
     delirium
    0.63
    ic
    0.63
    POSITIVE LOGITS
    Manisha
    0.61
    Pairs
    0.59
    Sunglasses
    0.59
    Malaysia
    0.57
    Dare
    0.57
    Mehr
    0.57
    Missing
    0.56
    Liste
    0.56
    Cara
    0.56
    Seeds
    0.55
    Act Density 0.023%

    No Known Activations