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

    Neuronpedia

    INDEX
    Explanations

    word connectors in various languages

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    0.22
     I
    0.22
     हैज
    0.21
    ↵
    0.20
     formée
    0.20
    idać
    0.20
    -
    0.20
     So
    0.20
     Greg
    0.19
     Welch
    0.19
    POSITIVE LOGITS
     এবং
    0.37
     и
    0.32
    នៃ
    0.32
     và
    0.31
     மற்றும்
    0.31
     અને
    0.31
     और
    0.30
     και
    0.30
    และ
    0.29
     आणि
    0.29
    Act Density 0.255%

    No Known Activations