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

    Neuronpedia

    INDEX
    Explanations

    there is a

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    从未
    0.39
     precious
    0.37
    solving
    0.36
     perish
    0.35
    美味しい
    0.35
    ொ
    0.35
     absorbed
    0.34
    딸
    0.34
    踊
    0.34
    wo
    0.34
    POSITIVE LOGITS
     необходимости
    0.68
     necessidade
    0.66
     необходимость
    0.66
     need
    0.63
     necesidad
    0.63
     possibility
    0.60
     posibilidad
    0.59
     impossibility
    0.59
     Möglichkeit
    0.57
     possibilidade
    0.57
    Act Density 0.007%

    No Known Activations