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

    Neuronpedia

    INDEX
    Explanations

    very good, crying out loud

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Evolutionary
    0.34
    ంబేద్
    0.33
     dueDate
    0.33
    érapie
    0.32
     CXCR
    0.32
     bidirectional
    0.31
     séqu
    0.31
    ༢
    0.31
     Elovl
    0.30
    𝕄
    0.30
    POSITIVE LOGITS
     Galer
    0.34
     Keg
    0.34
     Spike
    0.32
     Kirk
    0.32
    '.
    0.31
     देम
    0.30
    wag
    0.28
    ↵
    0.28
     Bailey
    0.28
     colonel
    0.28
    Act Density 0.000%

    No Known Activations