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

    Neuronpedia

    INDEX
    Explanations

    foreign entities

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     starters
    0.43
     это
    0.39
     fluke
    0.38
     circumst
    0.38
     этому
    0.37
     этих
    0.36
     sulphide
    0.36
     circumstance
    0.36
     likeness
    0.35
     adj
    0.35
    POSITIVE LOGITS
    他の
    0.53
     OTHER
    0.50
     Massacre
    0.48
    其他
    0.48
     інших
    0.48
    其他的
    0.47
    לחמת
    0.46
    ﺯ
    0.46
     अन्य
    0.45
     Throat
    0.45
    Act Density 0.001%

    No Known Activations