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

    Neuronpedia

    INDEX
    Explanations

    challenges, oneself, negatively, suit, burrow

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    at
    1.43
    `${
    1.40
    جراء
    1.27
    Salv
    1.27
    ज
    1.18
    फोन
    1.16
    Hasil
    1.14
    ‛
    1.13
    Ар
    1.12
    Voids
    1.12
    POSITIVE LOGITS
     lush
    1.22
     enmity
    1.15
    ული
    1.08
     loving
    1.07
    මාණය
    1.02
     growth
    1.02
     receptive
    1.01
     liking
    1.01
     mis
    1.00
    ফেসর
    0.99
    Act Density 0.001%

    No Known Activations