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

    Neuronpedia

    INDEX
    Explanations

    necessity and dependence

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Peut
    0.42
     může
    0.39
     indicates
    0.38
    圄
    0.38
     قوس
    0.38
    aturing
    0.37
    อาจ
    0.37
     Buch
    0.36
    BufOffset
    0.36
     рә
    0.36
    POSITIVE LOGITS
     необходи
    0.50
     necesitamos
    0.47
     Именно
    0.47
     необходимо
    0.45
     indispensables
    0.45
     NEED
    0.45
     niezbęd
    0.44
     indispens
    0.43
     indispensable
    0.43
    NEED
    0.43
    Act Density 0.118%

    No Known Activations