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

    Neuronpedia

    INDEX
    Explanations

    ` code abbreviations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     RAM
    1.07
    RAM
    1.06
     NAS
    1.04
     NAP
    1.03
     RAID
    1.02
    IRA
    1.01
     SPAC
    1.01
     RICO
    1.01
    ZIP
    1.00
    SIB
    1.00
    POSITIVE LOGITS
     bn
    2.05
     tm
    2.00
     fn
    1.99
     tn
    1.92
     nm
    1.91
     cnt
    1.89
     md
    1.88
     cn
    1.88
     cm
    1.88
     lst
    1.87
    Act Density 1.051%

    No Known Activations