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

    Neuronpedia

    INDEX
    Explanations

    lists with Low, Medium, High

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     korzyst
    0.35
     Rout
    0.34
    뚜
    0.34
     आव
    0.34
     agon
    0.34
    륭
    0.34
     تتح
    0.33
    है
    0.33
     حافظ
    0.32
     Maschinen
    0.32
    POSITIVE LOGITS
    AMI
    0.46
    credential
    0.43
    Mfg
    0.42
    BK
    0.42
    NIH
    0.42
    Posted
    0.41
    PIA
    0.41
    committees
    0.40
    EH
    0.40
     csp
    0.40
    Act Density 0.016%

    No Known Activations