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

    Neuronpedia

    INDEX
    Explanations

    comparisons to other items

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     identical
    0.51
     paredes
    0.51
     entfernen
    0.51
    м
    0.51
    𝐨
    0.51
     emblematic
    0.50
    ERS
    0.50
     nodo
    0.49
     células
    0.49
    to
    0.48
    POSITIVE LOGITS
     than
    0.59
     чем
    0.54
     competitiveness
    0.52
     cereals
    0.51
    igde
    0.50
    Than
    0.49
     fad
    0.49
     tonnage
    0.48
     tycoon
    0.48
     decât
    0.48
    Act Density 0.227%

    No Known Activations