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

    Neuronpedia

    INDEX
    Explanations

    models and versions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    semanticweb
    0.83
     موقف
    0.78
    przy
    0.77
    Buddhist
    0.77
     hobbies
    0.77
     ideas
    0.76
     niezbęd
    0.76
     Buddhist
    0.74
     держави
    0.74
     approaches
    0.74
    POSITIVE LOGITS
     versions
    1.62
     version
    1.62
    版本
    1.54
     discontinued
    1.43
     edition
    1.43
     Versions
    1.42
     editions
    1.41
     Version
    1.39
     版本
    1.38
    版本的
    1.38
    Act Density 0.368%

    No Known Activations