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

    Neuronpedia

    INDEX
    Explanations

    explaining or describing

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     perdre
    0.40
     ausschließlich
    0.39
     verhindert
    0.37
     ವಿರುದ್ಧ
    0.37
     laissant
    0.37
    に対する
    0.36
     deaktiv
    0.36
    ேத்க
    0.35
    えない
    0.35
     conseguenza
    0.35
    POSITIVE LOGITS
    details
    0.39
    upakan
    0.38
    ada
    0.38
     consist
    0.37
     details
    0.37
    Format
    0.37
     gồm
    0.37
     consists
    0.37
     equipped
    0.37
     Details
    0.37
    Act Density 0.446%

    No Known Activations