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

    Neuronpedia

    INDEX
    Explanations

    distinguishing from others

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    tion
    0.47
    esity
    0.46
    ity
    0.44
    arnia
    0.40
    amay
    0.40
    act
    0.39
    vency
    0.39
    achine
    0.39
    adas
    0.39
    kx
    0.38
    POSITIVE LOGITS
     подобных
    0.62
     contenders
    0.60
     contemporaries
    0.58
     competitors
    0.58
    常見
    0.56
     usual
    0.54
     similaires
    0.54
     similares
    0.53
     innych
    0.52
     подобные
    0.52
    Act Density 0.097%

    No Known Activations