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

    Neuronpedia

    INDEX
    Explanations

    health issues

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    iede
    1.49
    oring
    1.48
    ored
    1.43
    ager
    1.35
    ews
    1.33
    ors
    1.32
    attutto
    1.32
    You
    1.30
    ated
    1.30
    ieren
    1.30
    POSITIVE LOGITS
     goin
    1.25
     horrid
    1.21
     đc
    1.12
     ticked
    1.07
    himanyu
    1.06
     travelled
    1.05
     flanked
    1.04
     recieve
    1.02
     rigged
    1.02
     skipped
    1.01
    Act Density 0.052%

    No Known Activations