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

    Neuronpedia

    INDEX
    Explanations

    auto;

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    AddRange
    0.41
     üzere
    0.40
     aussch
    0.38
    olge
    0.37
    ואה
    0.36
     jardin
    0.35
     vortices
    0.35
     esperado
    0.35
    侈
    0.35
     Prancis
    0.35
    POSITIVE LOGITS
    валися
    0.44
     capping
    0.41
     starring
    0.39
    aying
    0.38
    atum
    0.38
    𝐔
    0.38
    當
    0.37
    orphism
    0.37
     Championship
    0.36
     Մ
    0.36
    Act Density 0.001%

    No Known Activations