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

    Neuronpedia

    INDEX
    Explanations

    social issues and concepts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ē
    0.37
     specifico
    0.34
     다음과
    0.33
     घेऊ
    0.33
     দীপ
    0.32
     dodat
    0.32
     ქვ
    0.32
     क्रमशः
    0.32
    Applying
    0.31
     Loki
    0.31
    POSITIVE LOGITS
    !”
    0.48
    ”,
    0.46
    ”，
    0.43
    .”
    0.42
    ”.
    0.42
    ”،
    0.42
    atmosphère
    0.40
    !"
    0.40
    ”:
    0.40
    »،
    0.38
    Act Density 0.017%

    No Known Activations