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

    Neuronpedia

    INDEX
    Explanations

    become

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    naj
    0.73
     作为
    0.70
    权益
    0.69
     donna
    0.68
    으면
    0.68
     lymphomas
    0.67
    igueur
    0.66
     html
    0.66
    စေ
    0.64
     disjoint
    0.64
    POSITIVE LOGITS
    Ocean
    0.73
    ocean
    0.70
     ocean
    0.69
    Só
    0.68
    FocusValue
    0.67
     नदी
    0.67
    vate
    0.67
     নদী
    0.67
    hurricane
    0.66
    ahua
    0.65
    Act Density 0.001%

    No Known Activations