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

    Neuronpedia

    INDEX
    Explanations

    book titles and academic subjects

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     potentially
    0.93
     healthcare
    0.87
     a
    0.86
     deep
    0.85
     IS
    0.84
     societal
    0.79
     resilience
    0.76
     mindset
    0.76
     the
    0.75
     real
    0.75
    POSITIVE LOGITS
    <unused2189>
    1.22
    ]|
    1.16
    𒂮
    1.13
    <unused290>
    1.02
    <unused1882>
    1.02
    𒐸
    1.02
    <unused2089>
    1.02
    <unused2115>
    1.01
    <unused305>
    1.00
    <unused203>
    0.99
    Act Density 0.007%

    No Known Activations