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

    Neuronpedia

    INDEX
    Explanations

    helping hand or thing

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     influenza
    0.48
     acidity
    0.48
     absentee
    0.48
     invoicing
    0.48
    t
    0.48
     angle
    0.47
     allowance
    0.47
     arbitration
    0.47
     accreditation
    0.46
     advice
    0.46
    POSITIVE LOGITS
     quienes
    0.58
     conjunto
    0.56
     sudah
    0.54
     మేము
    0.54
     criado
    0.54
     camiseta
    0.53
    hiddenMap
    0.53
     Sudah
    0.53
     amenazas
    0.52
     који
    0.52
    Act Density 0.001%

    No Known Activations