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

    Neuronpedia

    INDEX
    Explanations

    exploring relationships and concepts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Invitational
    0.46
     Acting
    0.42
     hatt
    0.41
     invit
    0.39
     firsthand
    0.39
     lovingly
    0.39
    adinya
    0.38
     acting
    0.38
    mittedly
    0.38
     यून
    0.37
    POSITIVE LOGITS
    huge
    0.46
    room
    0.46
    Huge
    0.45
     решение
    0.40
    iere
    0.40
    solution
    0.40
    ammable
    0.40
    ages
    0.39
     huge
    0.39
    about
    0.39
    Act Density 0.002%

    No Known Activations