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

    Neuronpedia

    INDEX
    Explanations

    URLs

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    निश्ड
    0.37
     qualifications
    0.33
     psychedelic
    0.32
    澼
    0.31
    ängt
    0.31
     apopt
    0.30
     metaverse
    0.30
    mêmes
    0.30
     گے۔
    0.30
     amyg
    0.29
    POSITIVE LOGITS
    -_
    0.40
     _
    0.36
    كون
    0.32
    No
    0.32
     _,
    0.30
    СО
    0.29
    SO
    0.29
    LA
    0.29
    _{-}
    0.28
    ]_
    0.28
    Act Density 0.001%

    No Known Activations