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

    Neuronpedia

    INDEX
    Explanations

    commit history

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Hydrochloride
    0.68
    Algorithm
    0.67
    ReLU
    0.66
    ಅ
    0.64
    ğer
    0.64
    Algorithms
    0.64
     Hydrochloride
    0.64
    அ
    0.63
     Paryayvachi
    0.62
    מת
    0.61
    POSITIVE LOGITS
    -
    0.92
    able
    0.92
     being
    0.91
    ful
    0.87
    iveness
    0.86
    fulness
    0.84
    ous
    0.84
    less
    0.83
     despite
    0.82
     they
    0.81
    Act Density 1.562%

    No Known Activations