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

    Neuronpedia

    INDEX
    Explanations

    you want me to

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    mat
    0.77
     ಹೆ
    0.73
    मैट
    0.72
     Mat
    0.71
    Matt
    0.71
     एंट
    0.70
    𝑚
    0.69
    mc
    0.68
    unload
    0.67
    MAT
    0.67
    POSITIVE LOGITS
     po
    0.61
     reik
    0.58
    遇
    0.56
     vorbei
    0.54
    poke
    0.54
     Put
    0.53
     অসম্ভব
    0.53
     Po
    0.53
     poz
    0.53
    w
    0.52
    Act Density 0.165%

    No Known Activations