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

    Neuronpedia

    INDEX
    Explanations

    positive sentiment or description

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     following
    0.91
     assessments
    0.86
     essentials
    0.82
     tests
    0.81
     “
    0.77
     solutions
    0.76
     statements
    0.74
     Following
    0.74
     discussions
    0.74
     vaccines
    0.72
    POSITIVE LOGITS
     eyeball
    0.83
    Folding
    0.75
    Wonderful
    0.73
    Sub
    0.73
    otika
    0.72
     hierro
    0.69
     eigenes
    0.67
     ব্ল
    0.67
    ಾರದ
    0.66
    Vintage
    0.66
    Act Density 0.000%

    No Known Activations