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

    Neuronpedia

    INDEX
    Explanations

    academic research and services

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     FCS
    0.46
     earnestly
    0.44
     FCA
    0.43
    MCS
    0.42
     ESM
    0.41
     DMS
    0.37
     rigorously
    0.36
     GBM
    0.36
    erler
    0.36
     Halle
    0.36
    POSITIVE LOGITS
     ehm
    0.40
    Przyp
    0.36
    ahah
    0.36
    意思是
    0.36
    enc
    0.36
    </h1>
    0.35
     &$\
    0.35
    iteit
    0.35
     $(\
    0.34
     Happens
    0.34
    Act Density 0.031%

    No Known Activations