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

    Neuronpedia

    INDEX
    Explanations

    included or helps

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Cred
    0.37
     Outs
    0.34
    Cred
    0.34
    iculation
    0.31
     Holly
    0.30
     brahm
    0.30
     अन
    0.29
     outsource
    0.29
     '-',
    0.29
     slov
    0.29
    POSITIVE LOGITS
     landlab
    0.35
     tiež
    0.35
     także
    0.34
     أيضًا
    0.34
    िसोदिया
    0.34
     rebuttal
    0.34
     також
    0.33
     tadi
    0.33
     geophysical
    0.33
    yrıca
    0.32
    Act Density 0.008%

    No Known Activations