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

    Neuronpedia

    INDEX
    Explanations

    ability to verb

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Need
    0.98
    Need
    0.97
     needing
    0.90
    need
    0.88
     potrebno
    0.87
     nécessité
    0.86
     necessità
    0.84
     необходимости
    0.83
     необходимость
    0.81
    が必要
    0.80
    POSITIVE LOGITS
     easily
    1.83
     certainly
    1.55
     readily
    1.42
     comfortably
    1.38
     definitely
    1.38
    easily
    1.37
     often
    1.33
     safely
    1.32
     facilmente
    1.29
     fácilmente
    1.29
    Act Density 0.577%

    No Known Activations