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

    Neuronpedia

    INDEX
    Explanations

    police report

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    пи
    0.63
     możemy
    0.59
    ری
    0.57
    ле
    0.56
    τό
    0.56
    кість
    0.55
    ці
    0.54
    нется
    0.53
    льзя
    0.52
    льных
    0.51
    POSITIVE LOGITS
    c
    0.60
     iris
    0.54
    j
    0.54
    h
    0.54
     छोटी
    0.53
    ies
    0.53
     chhoti
    0.52
    isal
    0.51
     nuevas
    0.50
    ine
    0.50
    Act Density 0.001%

    No Known Activations