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

    Neuronpedia

    INDEX
    Explanations

    statement termination

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     gyn
    0.44
    Kya
    0.38
     Mans
    0.37
    াড়াও
    0.37
     acaso
    0.37
     aktiv
    0.37
    perror
    0.37
    出来ない
    0.36
     moż
    0.36
     pseud
    0.36
    POSITIVE LOGITS
    лежа
    0.40
     ኢን
    0.40
    льные
    0.39
     ley
    0.36
    lles
    0.35
     Ogden
    0.35
     concentrated
    0.35
    ступа
    0.35
     إل
    0.34
     मैकेन
    0.34
    Act Density 0.001%

    No Known Activations