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

    Neuronpedia

    INDEX
    Explanations

    programming languages and tools

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    సూరు
    0.35
     đỏ
    0.34
     વખત
    0.34
     nationalities
    0.33
     ሙሉ
    0.33
     όλ
    0.33
    াড়াও
    0.33
    omitem
    0.33
     cultivators
    0.33
    oflav
    0.32
    POSITIVE LOGITS
    ،
    0.48
     using
    0.46
    ，
    0.39
    ‬
    0.38
    ，《
    0.38
    。
    0.38
     ,
    0.38
     menggunakan
    0.38
    Dz
    0.37
    において
    0.36
    Act Density 0.240%

    No Known Activations