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

    Neuronpedia

    INDEX
    Explanations

    legislative acts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    és
    0.64
    ILL
    0.57
    ời
    0.57
    OBER
    0.55
    roffenen
    0.55
    borough
    0.55
    𝚘
    0.55
     ellos
    0.54
    esso
    0.53
    その
    0.53
    POSITIVE LOGITS
    ;
    0.58
    vette
    0.55
     mu
    0.55
     DOT
    0.48
     toer
    0.48
     reshape
    0.48
     başlat
    0.47
     السيا
    0.46
    9
    0.46
     isn
    0.46
    Act Density 0.001%

    No Known Activations