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

    Neuronpedia

    INDEX
    Explanations

    current events

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     भएको
    0.50
     색
    0.48
     শব
    0.46
    েক্টর
    0.46
    nienie
    0.46
    altungen
    0.46
    ㅋㅋ
    0.46
     wenige
    0.44
    ައި
    0.44
     ০
    0.44
    POSITIVE LOGITS
    IS
    0.53
    یم
    0.53
    tel
    0.48
    Japanese
    0.48
    ستر
    0.46
     Sta
    0.46
    is
    0.45
    Sta
    0.45
    mapStateToProps
    0.45
     tail
    0.45
    Act Density 0.000%

    No Known Activations