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

    Neuronpedia

    INDEX
    Explanations

    job titles

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     nft
    0.39
     ग्रहों
    0.39
     之
    0.39
     जोड़
    0.38
     vortices
    0.37
     आईपीएल
    0.37
     भंड
    0.37
     saranam
    0.37
     परीक्षण
    0.36
     ALSO
    0.36
    POSITIVE LOGITS
    none
    0.47
    None
    0.46
    Unknown
    0.46
    yes
    0.44
     None
    0.44
    localhost
    0.44
    INR
    0.43
    NaN
    0.43
    unknown
    0.43
    False
    0.43
    Act Density 0.019%

    No Known Activations