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

    Neuronpedia

    INDEX
    Explanations

    end of sentence markers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    𝖽
    0.32
    commitment
    0.32
    Did
    0.30
    Fund
    0.30
    Firstly
    0.30
    Ded
    0.30
    тын
    0.30
    Primero
    0.29
    first
    0.29
     primero
    0.29
    POSITIVE LOGITS
     Here
    0.46
     Below
    0.42
     Voici
    0.42
     below
    0.38
     Note
    0.38
     here
    0.38
     voici
    0.36
     also
    0.35
     aqui
    0.34
     Also
    0.34
    Act Density 0.001%

    No Known Activations