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

    Neuronpedia

    INDEX
    Explanations

    authors and concepts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ಮಕ್ಕಳ
    0.43
     unreal
    0.38
     denotes
    0.37
    agana
    0.37
    ApiParam
    0.37
     agr
    0.37
     יל
    0.37
     பெரிய
    0.36
    குழந்த
    0.36
     pays
    0.36
    POSITIVE LOGITS
    馈
    0.39
     Jamb
    0.38
    ўцаў
    0.38
    pcs
    0.38
     قاب
    0.37
     забра
    0.37
     zab
    0.37
     Charter
    0.37
    čet
    0.36
    चारिक
    0.36
    Act Density 0.004%

    No Known Activations