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

    Neuronpedia

    INDEX
    Explanations

    code, hardware, relationships

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Fund
    0.45
    у
    0.45
    ate
    0.44
    pl
    0.44
     validate
    0.40
    opens
    0.40
    ot
    0.40
    ре
    0.40
    ante
    0.40
    orse
    0.39
    POSITIVE LOGITS
     biopic
    0.51
    🏒
    0.49
     మూవీ
    0.47
    受伤
    0.47
     ().
    0.46
     roupas
    0.46
     tandis
    0.46
     videogame
    0.46
     quotidienne
    0.45
     pouvaient
    0.45
    Act Density 0.002%

    No Known Activations