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

    Neuronpedia

    INDEX
    Explanations

    LaTeX environments

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    фы
    0.43
     섹
    0.41
     appendices
    0.39
    oradi
    0.38
     env
    0.38
     Tore
    0.37
     sections
    0.37
    섹
    0.36
     section
    0.36
    Fach
    0.35
    POSITIVE LOGITS
    align
    0.44
    Align
    0.38
    ROWN
    0.37
     aligned
    0.37
     Нужно
    0.37
    blue
    0.37
    apal
    0.37
     जंगली
    0.36
    ño
    0.36
    latex
    0.36
    Act Density 0.000%

    No Known Activations