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

    Neuronpedia

    INDEX
    Explanations

    license and schema information

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     kullanım
    0.32
     araştırm
    0.30
    abbanti
    0.29
    𒋾
    0.28
    いますが
    0.27
     आपका
    0.27
    gunakan
    0.27
    alassem
    0.27
     diversité
    0.27
     murderous
    0.26
    POSITIVE LOGITS
    ↵
    0.30
     acts
    0.25
     vital
    0.25
    ，
    0.24
     ကို
    0.24
     fits
    0.24
    <
    0.24
    ↵↵
    0.24
     act
    0.23
     Reply
    0.22
    Act Density 0.001%

    No Known Activations